v25-0003-Make-archiver-process-an-auxiliary-process.patch

From aad88158d889e92a5c46bf47e94e87f7b6a09a36 Mon Sep 17 00:00:00 2001
From: Thomas Munro <thomas.munro@gmail.com>
Date: Thu, 19 Mar 2020 13:40:17 +1300
Subject: [PATCH v25 3/5] Make archiver process an auxiliary process.

Author: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Discussion: https://postgre.es/m/20180629.173418.190173462.horiguchi.kyotaro%40lab.ntt.co.jp
---
 src/backend/bootstrap/bootstrap.c   |  8 +++
 src/backend/postmaster/pgarch.c     | 98 +++++++----------------------
 src/backend/postmaster/postmaster.c | 43 ++++++++-----
 src/backend/utils/init/miscinit.c   |  6 +-
 src/include/miscadmin.h             |  2 +
 src/include/postmaster/pgarch.h     |  4 +-
 6 files changed, 66 insertions(+), 95 deletions(-)

diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..423bf99958 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;
@@ -443,6 +446,11 @@ 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 01ffd6513c..589637c2de 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,
@@ -250,8 +179,27 @@ 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/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/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c
index a7b7b12249..1d1ebd6a23 100644
--- a/src/backend/utils/init/miscinit.c
+++ b/src/backend/utils/init/miscinit.c
@@ -199,6 +199,9 @@ GetBackendTypeDesc(BackendType backendType)
 		case B_INVALID:
 			backendDesc = "not initialized";
 			break;
+		case B_ARCHIVER:
+			backendDesc = "archiver";
+			break;
 		case B_AUTOVAC_LAUNCHER:
 			backendDesc = "autovacuum launcher";
 			break;
@@ -229,9 +232,6 @@ GetBackendTypeDesc(BackendType backendType)
 		case B_WAL_WRITER:
 			backendDesc = "walwriter";
 			break;
-		case B_ARCHIVER:
-			backendDesc = "archiver";
-			break;
 		case B_STATS_COLLECTOR:
 			backendDesc = "stats collector";
 			break;
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 */
-- 
2.20.1