postmaster.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

	 * This check is an essential part of the interlock that prevents two
	 * postmasters from starting in the same directory (see CreateLockFile()).
	 * Do not remove or weaken it.
	 *
	 * XXX can we safely enable this check on Windows?
	 */
#if !defined(WIN32) && !defined(__CYGWIN__)
	if (stat_buf.st_uid != geteuid())
		ereport(FATAL,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("data directory \"%s\" has wrong ownership",
						DataDir),
				 errhint("The server must be started by the user that owns the data directory.")));
#endif

	/*
	 * Check if the directory has group or world access.  If so, reject.
	 *
	 * It would be possible to allow weaker constraints (for example, allow
	 * group access) but we cannot make a general assumption that that is
	 * okay; for example there are platforms where nearly all users
	 * customarily belong to the same group.  Perhaps this test should be
	 * configurable.
	 *
	 * XXX temporarily suppress check when on Windows, because there may not
	 * be proper support for Unix-y file permissions.  Need to think of a
	 * reasonable check to apply on Windows.
	 */
#if !defined(WIN32) && !defined(__CYGWIN__)
	if (stat_buf.st_mode & (S_IRWXG | S_IRWXO))
		ereport(FATAL,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("data directory \"%s\" has group or world access",
						DataDir),
				 errdetail("Permissions should be u=rwx (0700).")));
#endif

	/* Look for PG_VERSION before looking for pg_control */
	ValidatePgVersion(DataDir);

	snprintf(path, sizeof(path), "%s/global/pg_control", DataDir);

	fp = AllocateFile(path, PG_BINARY_R);
	if (fp == NULL)
	{
		write_stderr("%s: could not find the database system\n"
					 "Expected to find it in the directory \"%s\",\n"
					 "but could not open file \"%s\": %s\n",
					 progname, DataDir, path, strerror(errno));
		ExitPostmaster(2);
	}
	FreeFile(fp);
}


#ifdef USE_BONJOUR

/*
 * empty callback function for DNSServiceRegistrationCreate()
 */
static void
reg_reply(DNSServiceRegistrationReplyErrorType errorCode, void *context)
{

}
#endif   /* USE_BONJOUR */


/*
 * Fork away from the controlling terminal (-S option)
 */
static void
pmdaemonize(void)
{
#ifndef WIN32
	int			i;
	pid_t		pid;

	pid = fork_process();
	if (pid == (pid_t) -1)
	{
		write_stderr("%s: could not fork background process: %s\n",
					 progname, strerror(errno));
		ExitPostmaster(1);
	}
	else if (pid)
	{							/* parent */
		/* Parent should just exit, without doing any atexit cleanup */
		_exit(0);
	}

	MyProcPid = PostmasterPid = getpid();		/* reset PID vars to child */

/* GH: If there's no setsid(), we hopefully don't need silent mode.
 * Until there's a better solution.
 */
#ifdef HAVE_SETSID
	if (setsid() < 0)
	{
		write_stderr("%s: could not dissociate from controlling TTY: %s\n",
					 progname, strerror(errno));
		ExitPostmaster(1);
	}
#endif
	i = open(NULL_DEV, O_RDWR);
	dup2(i, 0);
	dup2(i, 1);
	dup2(i, 2);
	close(i);
#else							/* WIN32 */
	/* not supported */
	elog(FATAL, "SilentMode not supported under WIN32");
#endif   /* WIN32 */
}


/*
 * Print out help message
 */
static void
usage(const char *progname)
{
	printf(_("%s is the PostgreSQL server.\n\n"), progname);
	printf(_("Usage:\n  %s [OPTION]...\n\n"), progname);
	printf(_("Options:\n"));
#ifdef USE_ASSERT_CHECKING
	printf(_("  -A 1|0          enable/disable run-time assert checking\n"));
#endif
	printf(_("  -B NBUFFERS     number of shared buffers\n"));
	printf(_("  -c NAME=VALUE   set run-time parameter\n"));
	printf(_("  -d 1-5          debugging level\n"));
	printf(_("  -D DATADIR      database directory\n"));
	printf(_("  -F              turn fsync off\n"));
	printf(_("  -h HOSTNAME     host name or IP address to listen on\n"));
	printf(_("  -i              enable TCP/IP connections\n"));
	printf(_("  -k DIRECTORY    Unix-domain socket location\n"));
#ifdef USE_SSL
	printf(_("  -l              enable SSL connections\n"));
#endif
	printf(_("  -N MAX-CONNECT  maximum number of allowed connections\n"));
	printf(_("  -o OPTIONS      pass \"OPTIONS\" to each server process\n"));
	printf(_("  -p PORT         port number to listen on\n"));
	printf(_("  -S              silent mode (start in background without logging output)\n"));
	printf(_("  --help          show this help, then exit\n"));
	printf(_("  --version       output version information, then exit\n"));

	printf(_("\nDeveloper options:\n"));
	printf(_("  -n              do not reinitialize shared memory after abnormal exit\n"));
	printf(_("  -s              send SIGSTOP to all backend servers if one dies\n"));

	printf(_("\nPlease read the documentation for the complete list of run-time\n"
	 "configuration settings and how to set them on the command line or in\n"
			 "the configuration file.\n\n"
			 "Report bugs to <[e-mail]>.\n"));
}


/*
 * Main idle loop of postmaster
 */
static int
ServerLoop(void)
{
	fd_set		readmask;
	int			nSockets;
	time_t		now,
				last_touch_time;
	struct timeval earlier,
				later;

	gettimeofday(&earlier, NULL);
	last_touch_time = time(NULL);

	nSockets = initMasks(&readmask);

	for (;;)
	{
		Port	   *port;
		fd_set		rmask;
		struct timeval timeout;
		int			selres;
		int			i;

		/*
		 * Wait for something to happen.
		 *
		 * We wait at most one minute, or the minimum autovacuum delay, to
		 * ensure that the other background tasks handled below get done even
		 * when no requests are arriving.
		 */
		memcpy((char *) &rmask, (char *) &readmask, sizeof(fd_set));

		timeout.tv_sec = Min(60, autovacuum_naptime);
		timeout.tv_usec = 0;

		PG_SETMASK(&UnBlockSig);

		selres = select(nSockets, &rmask, NULL, NULL, &timeout);

		/*
		 * Block all signals until we wait again.  (This makes it safe for our
		 * signal handlers to do nontrivial work.)
		 */
		PG_SETMASK(&BlockSig);

		if (selres < 0)
		{
			if (errno != EINTR && errno != EWOULDBLOCK)
			{
				ereport(LOG,
						(errcode_for_socket_access(),
						 errmsg("select() failed in postmaster: %m")));
				return STATUS_ERROR;
			}
		}

		/*
		 * New connection pending on any of our sockets? If so, fork a child
		 * process to deal with it.
		 */
		if (selres > 0)
		{
			/*
			 * Select a random seed at the time of first receiving a request.
			 */
			while (random_seed == 0)
			{
				gettimeofday(&later, NULL);

				/*
				 * We are not sure how much precision is in tv_usec, so we
				 * swap the high and low 16 bits of 'later' and XOR them with
				 * 'earlier'. On the off chance that the result is 0, we loop
				 * until it isn't.
				 */
				random_seed = earlier.tv_usec ^
					((later.tv_usec << 16) |
					 ((later.tv_usec >> 16) & 0xffff));
			}

			for (i = 0; i < MAXLISTEN; i++)
			{
				if (ListenSocket[i] == -1)
					break;
				if (FD_ISSET(ListenSocket[i], &rmask))
				{
					port = ConnCreate(ListenSocket[i]);
					if (port)
					{
						BackendStartup(port);

						/*
						 * We no longer need the open socket or port structure
						 * in this process
						 */
						StreamClose(port->sock);
						ConnFree(port);
					}
				}
			}
		}

		/* If we have lost the system logger, try to start a new one */
		if (SysLoggerPID == 0 && Redirect_stderr)
			SysLoggerPID = SysLogger_Start();

		/*
		 * If no background writer process is running, and we are not in a
		 * state that prevents it, start one.  It doesn't matter if this
		 * fails, we'll just try again later.
		 */
		if (BgWriterPID == 0 && StartupPID == 0 && !FatalError)
		{
			BgWriterPID = StartBackgroundWriter();
			/* If shutdown is pending, set it going */
			if (Shutdown > NoShutdown && BgWriterPID != 0)
				kill(BgWriterPID, SIGUSR2);
		}

		/*
		 * Start a new autovacuum process, if there isn't one running already.
		 * (It'll die relatively quickly.)  We check that it's not started too
		 * frequently in autovac_start.
		 */
		if (AutoVacuumingActive() && AutoVacPID == 0 &&
			StartupPID == 0 && !FatalError && Shutdown == NoShutdown)
			AutoVacPID = autovac_start();

		/* If we have lost the archiver, try to start a new one */
		if (XLogArchivingActive() && PgArchPID == 0 &&
			StartupPID == 0 && !FatalError && Shutdown == NoShutdown)
			PgArchPID = pgarch_start();

		/* If we have lost the stats collector, try to start a new one */
		if (PgStatPID == 0 &&
			StartupPID == 0 && !FatalError && Shutdown == NoShutdown)
			PgStatPID = pgstat_start();

		/*
		 * Touch the socket and lock file every 58 minutes, to ensure that
		 * they are not removed by overzealous /tmp-cleaning tasks.  We assume
		 * no one runs cleaners with cutoff times of less than an hour ...
		 */
		now = time(NULL);
		if (now - last_touch_time >= 58 * SECS_PER_MINUTE)
		{
			TouchSocketFile();
			TouchSocketLockFile();
			last_touch_time = now;
		}
	}
}


/*
 * Initialise the masks for select() for the ports we are listening on.
 * Return the number of sockets to listen on.
 */
static int
initMasks(fd_set *rmask)
{
	int			nsocks = -1;
	int			i;

	FD_ZERO(rmask);

	for (i = 0; i < MAXLISTEN; i++)
	{
		int			fd = ListenSocket[i];

		if (fd == -1)
			break;
		FD_SET(fd, rmask);
		if (fd > nsocks)
			nsocks = fd;
	}

	return nsocks + 1;
}


/*
 * Read the startup packet and do something according to it.
 *
 * Returns STATUS_OK or STATUS_ERROR, or might call ereport(FATAL) and
 * not return at all.
 *
 * (Note that ereport(FATAL) stuff is sent to the client, so only use it
 * if that's what you want.  Return STATUS_ERROR if you don't want to
 * send anything to the client, which would typically be appropriate
 * if we detect a communications failure.)
 */
static int
ProcessStartupPacket(Port *port, bool SSLdone)
{
	int32		len;
	void	   *buf;
	ProtocolVersion proto;
	MemoryContext oldcontext;

	if (pq_getbytes((char *) &len, 4) == EOF)
	{
		/*
		 * EOF after SSLdone probably means the client didn't like our
		 * response to NEGOTIATE_SSL_CODE.	That's not an error condition, so
		 * don't clutter the log with a complaint.
		 */
		if (!SSLdone)
			ereport(COMMERROR,
					(errcode(ERRCODE_PROTOCOL_VIOLATION),
					 errmsg("incomplete startup packet")));
		return STATUS_ERROR;
	}

	len = ntohl(len);
	len -= 4;

	if (len < (int32) sizeof(ProtocolVersion) ||
		len > MAX_STARTUP_PACKET_LENGTH)
	{
		ereport(COMMERROR,
				(errcode(ERRCODE_PROTOCOL_VIOLATION),
				 errmsg("invalid length of startup packet")));
		return STATUS_ERROR;
	}

	/*
	 * Allocate at least the size of an old-style startup packet, plus one
	 * extra byte, and make sure all are zeroes.  This ensures we will have
	 * null termination of all strings, in both fixed- and variable-length
	 * packet layouts.
	 */
	if (len <= (int32) sizeof(StartupPacket))
		buf = palloc0(sizeof(StartupPacket) + 1);
	else
		buf = palloc0(len + 1);

	if (pq_getbytes(buf, len) == EOF)
	{
		ereport(COMMERROR,
				(errcode(ERRCODE_PROTOCOL_VIOLATION),
				 errmsg("incomplete startup packet")));
		return STATUS_ERROR;
	}

	/*
	 * The first field is either a protocol version number or a special
	 * request code.
	 */
	port->proto = proto = ntohl(*((ProtocolVersion *) buf));

	if (proto == CANCEL_REQUEST_CODE)
	{
		processCancelRequest(port, buf);
		return 127;				/* XXX */
	}

	if (proto == NEGOTIATE_SSL_CODE && !SSLdone)
	{
		char		SSLok;

#ifdef USE_SSL
		/* No SSL when disabled or on Unix sockets */
		if (!EnableSSL || IS_AF_UNIX(port->laddr.addr.ss_family))
			SSLok = 'N';
		else
			SSLok = 'S';		/* Support for SSL */
#else
		SSLok = 'N';			/* No support for SSL */
#endif
		if (send(port->sock, &SSLok, 1, 0) != 1)
		{
			ereport(COMMERROR,
					(errcode_for_socket_access(),
					 errmsg("failed to send SSL negotiation response: %m")));
			return STATUS_ERROR;	/* close the connection */
		}

#ifdef USE_SSL
		if (SSLok == 'S' && secure_open_server(port) == -1)
			return STATUS_ERROR;
#endif
		/* regular startup packet, cancel, etc packet should follow... */
		/* but not another SSL negotiation request */
		return ProcessStartupPacket(port, true);
	}

	/* Could add additional special packet types here */

	/*
	 * Set FrontendProtocol now so that ereport() knows what format to send if
	 * we fail during startup.
	 */
	FrontendProtocol = proto;

	/* Check we can handle the protocol the frontend is using. */

	if (PG_PROTOCOL_MAJOR(proto) < PG_PROTOCOL_MAJOR(PG_PROTOCOL_EARLIEST) ||
		PG_PROTOCOL_MAJOR(proto) > PG_PROTOCOL_MAJOR(PG_PROTOCOL_LATEST) ||
		(PG_PROTOCOL_MAJOR(proto) == PG_PROTOCOL_MAJOR(PG_PROTOCOL_LATEST) &&
		 PG_PROTOCOL_MINOR(proto) > PG_PROTOCOL_MINOR(PG_PROTOCOL_LATEST)))
		ereport(FATAL,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("unsupported frontend protocol %u.%u: server supports %u.0 to %u.%u",
						PG_PROTOCOL_MAJOR(proto), PG_PROTOCOL_MINOR(proto),
						PG_PROTOCOL_MAJOR(PG_PROTOCOL_EARLIEST),
						PG_PROTOCOL_MAJOR(PG_PROTOCOL_LATEST),
						PG_PROTOCOL_MINOR(PG_PROTOCOL_LATEST))));

	/*
	 * Now fetch parameters out of startup packet and save them into the Port
	 * structure.  All data structures attached to the Port struct must be
	 * allocated in TopMemoryContext so that they won't disappear when we pass
	 * them to PostgresMain (see BackendRun).  We need not worry about leaking
	 * this storage on failure, since we aren't in the postmaster process
	 * anymore.
	 */
	oldcontext = MemoryContextSwitchTo(TopMemoryContext);

	if (PG_PROTOCOL_MAJOR(proto) >= 3)
	{
		int32		offset = sizeof(ProtocolVersion);

		/*
		 * Scan packet body for name/option pairs.	We can assume any string
		 * beginning within the packet body is null-terminated, thanks to
		 * zeroing extra byte above.
		 */
		port->guc_options = NIL;