/src/backend/postmaster/postmaster.c

Large files files are truncated, but you can click here to view the full file

/*-------------------------------------------------------------------------
 *
 * postmaster.c
 *	  This program acts as a clearing house for requests to the
 *	  POSTGRES system.  Frontend programs send a startup message
 *	  to the Postmaster and the postmaster uses the info in the
 *	  message to setup a backend process.
 *
 *	  The postmaster also manages system-wide operations such as
 *	  startup and shutdown. The postmaster itself doesn't do those
 *	  operations, mind you --- it just forks off a subprocess to do them
 *	  at the right times.  It also takes care of resetting the system
 *	  if a backend crashes.
 *
 *	  The postmaster process creates the shared memory and semaphore
 *	  pools during startup, but as a rule does not touch them itself.
 *	  In particular, it is not a member of the PGPROC array of backends
 *	  and so it cannot participate in lock-manager operations.  Keeping
 *	  the postmaster away from shared memory operations makes it simpler
 *	  and more reliable.  The postmaster is almost always able to recover
 *	  from crashes of individual backends by resetting shared memory;
 *	  if it did much with shared memory then it would be prone to crashing
 *	  along with the backends.
 *
 *	  When a request message is received, we now fork() immediately.
 *	  The child process performs authentication of the request, and
 *	  then becomes a backend if successful.  This allows the auth code
 *	  to be written in a simple single-threaded style (as opposed to the
 *	  crufty "poor man's multitasking" code that used to be needed).
 *	  More importantly, it ensures that blockages in non-multithreaded
 *	  libraries like SSL or PAM cannot cause denial of service to other
 *	  clients.
 *
 *
 * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/postmaster/postmaster.c
 *
 * NOTES
 *
 * Initialization:
 *		The Postmaster sets up shared memory data structures
 *		for the backends.
 *
 * Synchronization:
 *		The Postmaster shares memory with the backends but should avoid
 *		touching shared memory, so as not to become stuck if a crashing
 *		backend screws up locks or shared memory.  Likewise, the Postmaster
 *		should never block on messages from frontend clients.
 *
 * Garbage Collection:
 *		The Postmaster cleans up after backends if they have an emergency
 *		exit and/or core dump.
 *
 * Error Reporting:
 *		Use write_stderr() only for reporting "interactive" errors
 *		(essentially, bogus arguments on the command line).  Once the
 *		postmaster is launched, use ereport().
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include <unistd.h>
#include <signal.h>
#include <time.h>
#include <sys/wait.h>
#include <ctype.h>
#include <sys/stat.h>
#include <sys/socket.h>
#include <fcntl.h>
#include <sys/param.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <netdb.h>
#include <limits.h>

#ifdef HAVE_SYS_SELECT_H
#include <sys/select.h>
#endif

#ifdef USE_BONJOUR
#include <dns_sd.h>
#endif

#include "access/transam.h"
#include "access/xlog.h"
#include "bootstrap/bootstrap.h"
#include "catalog/pg_control.h"
#include "lib/ilist.h"
#include "libpq/auth.h"
#include "libpq/ip.h"
#include "libpq/libpq.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "pg_getopt.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "postmaster/bgworker_internals.h"
#include "postmaster/fork_process.h"
#include "postmaster/pgarch.h"
#include "postmaster/postmaster.h"
#include "postmaster/syslogger.h"
#include "replication/walsender.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/pg_shmem.h"
#include "storage/pmsignal.h"
#include "storage/proc.h"
#include "tcop/tcopprot.h"
#include "utils/builtins.h"
#include "utils/datetime.h"
#include "utils/dynamic_loader.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/timeout.h"

#ifdef EXEC_BACKEND
#include "storage/spin.h"
#endif


/*
 * Possible types of a backend. Beyond being the possible bkend_type values in
 * struct bkend, these are OR-able request flag bits for SignalSomeChildren()
 * and CountChildren().
 */
#define BACKEND_TYPE_NORMAL		0x0001	/* normal backend */
#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_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)

/*
 * List of active backends (or child processes anyway; we don't actually
 * know whether a given child has become a backend or is still in the
 * authorization phase).  This is used mainly to keep track of how many
 * children we have and send them appropriate signals when necessary.
 *
 * "Special" children such as the startup, bgwriter and autovacuum launcher
 * tasks are not in this list.  Autovacuum worker and walsender are in it.
 * Also, "dead_end" children are in it: these are children launched just for
 * the purpose of sending a friendly rejection message to a would-be client.
 * We must track them because they are attached to shared memory, but we know
 * they will never become live backends.  dead_end children are not assigned a
 * PMChildSlot.
 *
 * Background workers that request shared memory access during registration are
 * in this list, too.
 */
typedef struct bkend
{
	pid_t		pid;			/* process id of backend */
	long		cancel_key;		/* cancel key for cancels for this backend */
	int			child_slot;		/* PMChildSlot for this backend, if any */

	/*
	 * Flavor of backend or auxiliary process.  Note that BACKEND_TYPE_WALSND
	 * backends initially announce themselves as BACKEND_TYPE_NORMAL, so if
	 * bkend_type is normal, you should check for a recent transition.
	 */
	int			bkend_type;
	bool		dead_end;		/* is it going to send an error and quit? */
	bool		bgworker_notify;	/* gets bgworker start/stop notifications */
	dlist_node	elem;			/* list link in BackendList */
} Backend;

static dlist_head BackendList = DLIST_STATIC_INIT(BackendList);

#ifdef EXEC_BACKEND
static Backend *ShmemBackendArray;
#endif

BackgroundWorker *MyBgworkerEntry = NULL;



/* The socket number we are listening for connections on */
int			PostPortNumber;

/* The directory names for Unix socket(s) */
char	   *Unix_socket_directories;

/* The TCP listen address(es) */
char	   *ListenAddresses;

/*
 * ReservedBackends is the number of backends reserved for superuser use.
 * This number is taken out of the pool size given by MaxBackends so
 * number of backend slots available to non-superusers is
 * (MaxBackends - ReservedBackends).  Note what this really means is
 * "if there are <= ReservedBackends connections available, only superusers
 * can make new connections" --- pre-existing superuser connections don't
 * count against the limit.
 */
int			ReservedBackends;

/* The socket(s) we're listening to. */
#define MAXLISTEN	64
static pgsocket ListenSocket[MAXLISTEN];

/*
 * Set by the -o option
 */
static char ExtraOptions[MAXPGPATH];

/*
 * These globals control the behavior of the postmaster in case some
 * backend dumps core.  Normally, it kills all peers of the dead backend
 * and reinitializes shared memory.  By specifying -s or -n, we can have
 * the postmaster stop (rather than kill) peers and not reinitialize
 * shared data structures.  (Reinit is currently dead code, though.)
 */
static bool Reinit = true;
static int	SendStop = false;

/* still more option variables */
bool		EnableSSL = false;

int			PreAuthDelay = 0;
int			AuthenticationTimeout = 60;

bool		log_hostname;		/* for ps display and logging */
bool		Log_connections = false;
bool		Db_user_namespace = false;

bool		enable_bonjour = false;
char	   *bonjour_name;
bool		restart_after_crash = true;

/* PIDs of special child processes; 0 when not running */
static pid_t StartupPID = 0,
			BgWriterPID = 0,
			CheckpointerPID = 0,
			WalWriterPID = 0,
			WalReceiverPID = 0,
			AutoVacPID = 0,
			PgArchPID = 0,
			PgStatPID = 0,
			SysLoggerPID = 0;

/* Startup/shutdown state */
#define			NoShutdown		0
#define			SmartShutdown	1
#define			FastShutdown	2
#define			ImmediateShutdown	3

static int	Shutdown = NoShutdown;

static bool FatalError = false; /* T if recovering from backend crash */
static bool RecoveryError = false;		/* T if WAL recovery failed */

/*
 * We use a simple state machine to control startup, shutdown, and
 * crash recovery (which is rather like shutdown followed by startup).
 *
 * After doing all the postmaster initialization work, we enter PM_STARTUP
 * state and the startup process is launched. The startup process begins by
 * reading the control file and other preliminary initialization steps.
 * In a normal startup, or after crash recovery, the startup process exits
 * with exit code 0 and we switch to PM_RUN state.  However, archive recovery
 * is handled specially since it takes much longer and we would like to support
 * hot standby during archive recovery.
 *
 * When the startup process is ready to start archive recovery, it signals the
 * postmaster, and we switch to PM_RECOVERY state. The background writer and
 * checkpointer are launched, while the startup process continues applying WAL.
 * If Hot Standby is enabled, then, after reaching a consistent point in WAL
 * redo, startup process signals us again, and we switch to PM_HOT_STANDBY
 * state and begin accepting connections to perform read-only queries.  When
 * archive recovery is finished, the startup process exits with exit code 0
 * and we switch to PM_RUN state.
 *
 * Normal child backends can only be launched when we are in PM_RUN or
 * PM_HOT_STANDBY state.  (We also allow launch of normal
 * child backends in PM_WAIT_BACKUP state, but only for superusers.)
 * In other states we handle connection requests by launching "dead_end"
 * child processes, which will simply send the client an error message and
 * quit.  (We track these in the BackendList so that we can know when they
 * are all gone; this is important because they're still connected to shared
 * memory, and would interfere with an attempt to destroy the shmem segment,
 * possibly leading to SHMALL failure when we try to make a new one.)
 * In PM_WAIT_DEAD_END state we are waiting for all the dead_end children
 * to drain out of the system, and therefore stop accepting connection
 * requests at all until the last existing child has quit (which hopefully
 * will not be very long).
 *
 * Notice that this state variable does not distinguish *why* we entered
 * states later than PM_RUN --- Shutdown and FatalError must be consulted
 * to find that out.  FatalError is never true in PM_RECOVERY_* or PM_RUN
 * states, nor in PM_SHUTDOWN states (because we don't enter those states
 * when trying to recover from a crash).  It can be true in PM_STARTUP state,
 * because we don't clear it until we've successfully started WAL redo.
 * Similarly, RecoveryError means that we have crashed during recovery, and
 * should not try to restart.
 */
typedef enum
{
	PM_INIT,					/* postmaster starting */
	PM_STARTUP,					/* waiting for startup subprocess */
	PM_RECOVERY,				/* in archive recovery mode */
	PM_HOT_STANDBY,				/* in hot standby mode */
	PM_RUN,						/* normal "database is alive" state */
	PM_WAIT_BACKUP,				/* waiting for online backup mode to end */
	PM_WAIT_READONLY,			/* waiting for read only backends to exit */
	PM_WAIT_BACKENDS,			/* waiting for live backends to exit */
	PM_SHUTDOWN,				/* waiting for checkpointer to do shutdown
								 * ckpt */
	PM_SHUTDOWN_2,				/* waiting for archiver and walsenders to
								 * finish */
	PM_WAIT_DEAD_END,			/* waiting for dead_end children to exit */
	PM_NO_CHILDREN				/* all important children have exited */
} PMState;

static PMState pmState = PM_INIT;

/* Start time of abort processing at immediate shutdown or child crash */
static time_t AbortStartTime;
#define SIGKILL_CHILDREN_AFTER_SECS		5

static bool ReachedNormalRunning = false;		/* T if we've reached PM_RUN */

bool		ClientAuthInProgress = false;		/* T during new-client
												 * authentication */

bool		redirection_done = false;	/* stderr redirected for syslogger? */

/* received START_AUTOVAC_LAUNCHER signal */
static volatile sig_atomic_t start_autovac_launcher = false;

/* the launcher needs to be signalled to communicate some condition */
static volatile bool avlauncher_needs_signal = false;

/* set when there's a worker that needs to be started up */
static volatile bool StartWorkerNeeded = true;
static volatile bool HaveCrashedWorker = false;

/*
 * State for assigning random salts and cancel keys.
 * Also, the global MyCancelKey passes the cancel key assigned to a given
 * backend from the postmaster to that backend (via fork).
 */
static unsigned int random_seed = 0;
static struct timeval random_start_time;

#ifdef USE_BONJOUR
static DNSServiceRef bonjour_sdref = NULL;
#endif

/*
 * postmaster.c - function prototypes
 */
static void unlink_external_pid_file(int status, Datum arg);
static void getInstallationPaths(const char *argv0);
static void checkDataDir(void);
static Port *ConnCreate(int serverFd);
static void ConnFree(Port *port);
static void reset_shared(int port);
static void SIGHUP_handler(SIGNAL_ARGS);
static void pmdie(SIGNAL_ARGS);
static void reaper(SIGNAL_ARGS);
static void sigusr1_handler(SIGNAL_ARGS);
static void startup_die(SIGNAL_ARGS);
static void dummy_handler(SIGNAL_ARGS);
static void StartupPacketTimeoutHandler(void);
static void CleanupBackend(int pid, int exitstatus);
static bool CleanupBackgroundWorker(int pid, int exitstatus);
static void HandleChildCrash(int pid, int exitstatus, const char *procname);
static void LogChildExit(int lev, const char *procname,
			 int pid, int exitstatus);
static void PostmasterStateMachine(void);
static void BackendInitialize(Port *port);
static void BackendRun(Port *port) __attribute__((noreturn));
static void ExitPostmaster(int status) __attribute__((noreturn));
static int	ServerLoop(void);
static int	BackendStartup(Port *port);
static int	ProcessStartupPacket(Port *port, bool SSLdone);
static void processCancelRequest(Port *port, void *pkt);
static int	initMasks(fd_set *rmask);
static void report_fork_failure_to_client(Port *port, int errnum);
static CAC_state canAcceptConnections(void);
static long PostmasterRandom(void);
static void RandomSalt(char *md5Salt);
static void signal_child(pid_t pid, int signal);
static bool SignalSomeChildren(int signal, int targets);
static bool SignalUnconnectedWorkers(int signal);
static void TerminateChildren(int signal);

#define SignalChildren(sig)			   SignalSomeChildren(sig, BACKEND_TYPE_ALL)

static int	CountChildren(int target);
static int	CountUnconnectedWorkers(void);
static void maybe_start_bgworker(void);
static bool CreateOptsFile(int argc, char *argv[], char *fullprogname);
static pid_t StartChildProcess(AuxProcType type);
static void StartAutovacuumWorker(void);
static void InitPostmasterDeathWatchHandle(void);

#ifdef EXEC_BACKEND

#ifdef WIN32
#define WNOHANG 0				/* ignored, so any integer value will do */

static pid_t waitpid(pid_t pid, int *exitstatus, int options);
static void WINAPI pgwin32_deadchild_callback(PVOID lpParameter, BOOLEAN TimerOrWaitFired);

static HANDLE win32ChildQueue;

typedef struct
{
	HANDLE		waitHandle;
	HANDLE		procHandle;
	DWORD		procId;
} win32_deadchild_waitinfo;
#endif   /* WIN32 */

static pid_t backend_forkexec(Port *port);
static pid_t internal_forkexec(int argc, char *argv[], Port *port);

/* Type for a socket that can be inherited to a client process */
#ifdef WIN32
typedef struct
{
	SOCKET		origsocket;		/* Original socket value, or PGINVALID_SOCKET
								 * if not a socket */
	WSAPROTOCOL_INFO wsainfo;
} InheritableSocket;
#else
typedef int InheritableSocket;
#endif

/*
 * Structure contains all variables passed to exec:ed backends
 */
typedef struct
{
	Port		port;
	InheritableSocket portsocket;
	char		DataDir[MAXPGPATH];
	pgsocket	ListenSocket[MAXLISTEN];
	long		MyCancelKey;
	int			MyPMChildSlot;
#ifndef WIN32
	unsigned long UsedShmemSegID;
#else
	HANDLE		UsedShmemSegID;
#endif
	void	   *UsedShmemSegAddr;
	slock_t    *ShmemLock;
	VariableCache ShmemVariableCache;
	Backend    *ShmemBackendArray;
#ifndef HAVE_SPINLOCKS
	PGSemaphore SpinlockSemaArray;
#endif
	LWLockPadded *MainLWLockArray;
	slock_t    *ProcStructLock;
	PROC_HDR   *ProcGlobal;
	PGPROC	   *AuxiliaryProcs;
	PGPROC	   *PreparedXactProcs;
	PMSignalData *PMSignalState;
	InheritableSocket pgStatSock;
	pid_t		PostmasterPid;
	TimestampTz PgStartTime;
	TimestampTz PgReloadTime;
	pg_time_t	first_syslogger_file_time;
	bool		redirection_done;
	bool		IsBinaryUpgrade;
	int			max_safe_fds;
	int			MaxBackends;
#ifdef WIN32
	HANDLE		PostmasterHandle;
	HANDLE		initial_signal_pipe;
	HANDLE		syslogPipe[2];
#else
	int			postmaster_alive_fds[2];
	int			syslogPipe[2];
#endif
	char		my_exec_path[MAXPGPATH];
	char		pkglib_path[MAXPGPATH];
	char		ExtraOptions[MAXPGPATH];
} BackendParameters;

static void read_backend_variables(char *id, Port *port);
static void restore_backend_variables(BackendParameters *param, Port *port);

#ifndef WIN32
static bool save_backend_variables(BackendParameters *param, Port *port);
#else
static bool save_backend_variables(BackendParameters *param, Port *port,
					   HANDLE childProcess, pid_t childPid);
#endif

static void ShmemBackendArrayAdd(Backend *bn);
static void ShmemBackendArrayRemove(Backend *bn);
#endif   /* EXEC_BACKEND */

#define StartupDataBase()		StartChildProcess(StartupProcess)
#define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
#define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
#define StartWalWriter()		StartChildProcess(WalWriterProcess)
#define StartWalReceiver()		StartChildProcess(WalReceiverProcess)

/* Macros to check exit status of a child process */
#define EXIT_STATUS_0(st)  ((st) == 0)
#define EXIT_STATUS_1(st)  (WIFEXITED(st) && WEXITSTATUS(st) == 1)

#ifndef WIN32
/*
 * File descriptors for pipe used to monitor if postmaster is alive.
 * First is POSTMASTER_FD_WATCH, second is POSTMASTER_FD_OWN.
 */
int			postmaster_alive_fds[2] = {-1, -1};
#else
/* Process handle of postmaster used for the same purpose on Windows */
HANDLE		PostmasterHandle;
#endif

/*
 * Postmaster main entry point
 */
void
PostmasterMain(int argc, char *argv[])
{
	int			opt;
	int			status;
	char	   *userDoption = NULL;
	bool		listen_addr_saved = false;
	int			i;
	char	   *output_config_variable = NULL;

	MyProcPid = PostmasterPid = getpid();

	MyStartTime = time(NULL);

	IsPostmasterEnvironment = true;

	/*
	 * for security, no dir or file created can be group or other accessible
	 */
	umask(S_IRWXG | S_IRWXO);

	/*
	 * By default, palloc() requests in the postmaster will be allocated in
	 * the PostmasterContext, which is space that can be recycled by backends.
	 * Allocated data that needs to be available to backends should be
	 * allocated in TopMemoryContext.
	 */
	PostmasterContext = AllocSetContextCreate(TopMemoryContext,
											  "Postmaster",
											  ALLOCSET_DEFAULT_MINSIZE,
											  ALLOCSET_DEFAULT_INITSIZE,
											  ALLOCSET_DEFAULT_MAXSIZE);
	MemoryContextSwitchTo(PostmasterContext);

	/* Initialize paths to installation files */
	getInstallationPaths(argv[0]);

	/*
	 * Set up signal handlers for the postmaster process.
	 *
	 * CAUTION: when changing this list, check for side-effects on the signal
	 * handling setup of child processes.  See tcop/postgres.c,
	 * bootstrap/bootstrap.c, postmaster/bgwriter.c, postmaster/walwriter.c,
	 * postmaster/autovacuum.c, postmaster/pgarch.c, postmaster/pgstat.c,
	 * postmaster/syslogger.c, postmaster/bgworker.c and
	 * postmaster/checkpointer.c.
	 */
	pqinitmask();
	PG_SETMASK(&BlockSig);

	pqsignal(SIGHUP, SIGHUP_handler);	/* reread config file and have
										 * children do same */
	pqsignal(SIGINT, pmdie);	/* send SIGTERM and shut down */
	pqsignal(SIGQUIT, pmdie);	/* send SIGQUIT and die */
	pqsignal(SIGTERM, pmdie);	/* wait for children and shut down */
	pqsignal(SIGALRM, SIG_IGN); /* ignored */
	pqsignal(SIGPIPE, SIG_IGN); /* ignored */
	pqsignal(SIGUSR1, sigusr1_handler); /* message from child process */
	pqsignal(SIGUSR2, dummy_handler);	/* unused, reserve for children */
	pqsignal(SIGCHLD, reaper);	/* handle child termination */
	pqsignal(SIGTTIN, SIG_IGN); /* ignored */
	pqsignal(SIGTTOU, SIG_IGN); /* ignored */
	/* ignore SIGXFSZ, so that ulimit violations work like disk full */
#ifdef SIGXFSZ
	pqsignal(SIGXFSZ, SIG_IGN); /* ignored */
#endif

	/*
	 * Options setup
	 */
	InitializeGUCOptions();

	opterr = 1;

	/*
	 * Parse command-line options.  CAUTION: keep this in sync with
	 * tcop/postgres.c (the option sets should not conflict) and with the
	 * common help() function in main/main.c.
	 */
	while ((opt = getopt(argc, argv, "A:B:bc:C:D:d:EeFf:h:ijk:lN:nOo:Pp:r:S:sTt:W:-:")) != -1)
	{
		switch (opt)
		{
			case 'A':
				SetConfigOption("debug_assertions", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'B':
				SetConfigOption("shared_buffers", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'b':
				/* Undocumented flag used for binary upgrades */
				IsBinaryUpgrade = true;
				break;

			case 'C':
				output_config_variable = strdup(optarg);
				break;

			case 'D':
				userDoption = strdup(optarg);
				break;

			case 'd':
				set_debug_options(atoi(optarg), PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'E':
				SetConfigOption("log_statement", "all", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'e':
				SetConfigOption("datestyle", "euro", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'F':
				SetConfigOption("fsync", "false", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'f':
				if (!set_plan_disabling_options(optarg, PGC_POSTMASTER, PGC_S_ARGV))
				{
					write_stderr("%s: invalid argument for option -f: \"%s\"\n",
								 progname, optarg);
					ExitPostmaster(1);
				}
				break;

			case 'h':
				SetConfigOption("listen_addresses", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'i':
				SetConfigOption("listen_addresses", "*", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'j':
				/* only used by interactive backend */
				break;

			case 'k':
				SetConfigOption("unix_socket_directories", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'l':
				SetConfigOption("ssl", "true", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'N':
				SetConfigOption("max_connections", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'n':
				/* Don't reinit shared mem after abnormal exit */
				Reinit = false;
				break;

			case 'O':
				SetConfigOption("allow_system_table_mods", "true", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'o':
				/* Other options to pass to the backend on the command line */
				snprintf(ExtraOptions + strlen(ExtraOptions),
						 sizeof(ExtraOptions) - strlen(ExtraOptions),
						 " %s", optarg);
				break;

			case 'P':
				SetConfigOption("ignore_system_indexes", "true", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'p':
				SetConfigOption("port", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'r':
				/* only used by single-user backend */
				break;

			case 'S':
				SetConfigOption("work_mem", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 's':
				SetConfigOption("log_statement_stats", "true", PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'T':

				/*
				 * In the event that some backend dumps core, send SIGSTOP,
				 * rather than SIGQUIT, to all its peers.  This lets the wily
				 * post_hacker collect core dumps from everyone.
				 */
				SendStop = true;
				break;

			case 't':
				{
					const char *tmp = get_stats_option_name(optarg);

					if (tmp)
					{
						SetConfigOption(tmp, "true", PGC_POSTMASTER, PGC_S_ARGV);
					}
					else
					{
						write_stderr("%s: invalid argument for option -t: \"%s\"\n",
									 progname, optarg);
						ExitPostmaster(1);
					}
					break;
				}

			case 'W':
				SetConfigOption("post_auth_delay", optarg, PGC_POSTMASTER, PGC_S_ARGV);
				break;

			case 'c':
			case '-':
				{
					char	   *name,
							   *value;

					ParseLongOption(optarg, &name, &value);
					if (!value)
					{
						if (opt == '-')
							ereport(ERROR,
									(errcode(ERRCODE_SYNTAX_ERROR),
									 errmsg("--%s requires a value",
											optarg)));
						else
							ereport(ERROR,
									(errcode(ERRCODE_SYNTAX_ERROR),
									 errmsg("-c %s requires a value",
											optarg)));
					}

					SetConfigOption(name, value, PGC_POSTMASTER, PGC_S_ARGV);
					free(name);
					if (value)
						free(value);
					break;
				}

			default:
				write_stderr("Try \"%s --help\" for more information.\n",
							 progname);
				ExitPostmaster(1);
		}
	}

	/*
	 * Postmaster accepts no non-option switch arguments.
	 */
	if (optind < argc)
	{
		write_stderr("%s: invalid argument: \"%s\"\n",
					 progname, argv[optind]);
		write_stderr("Try \"%s --help\" for more information.\n",
					 progname);
		ExitPostmaster(1);
	}

	/*
	 * Locate the proper configuration files and data directory, and read
	 * postgresql.conf for the first time.
	 */
	if (!SelectConfigFiles(userDoption, progname))
		ExitPostmaster(2);

	if (output_config_variable != NULL)
	{
		/*
		 * permission is handled because the user is reading inside the data
		 * dir
		 */
		puts(GetConfigOption(output_config_variable, false, false));
		ExitPostmaster(0);
	}

	/* Verify that DataDir looks reasonable */
	checkDataDir();

	/* And switch working directory into it */
	ChangeToDataDir();

	/*
	 * Check for invalid combinations of GUC settings.
	 */
	if (ReservedBackends >= MaxConnections)
	{
		write_stderr("%s: superuser_reserved_connections must be less than max_connections\n", progname);
		ExitPostmaster(1);
	}
	if (max_wal_senders >= MaxConnections)
	{
		write_stderr("%s: max_wal_senders must be less than max_connections\n", progname);
		ExitPostmaster(1);
	}
	if (XLogArchiveMode && wal_level == WAL_LEVEL_MINIMAL)
		ereport(ERROR,
				(errmsg("WAL archival (archive_mode=on) requires wal_level \"archive\", \"hot_standby\" or \"logical\"")));
	if (max_wal_senders > 0 && wal_level == WAL_LEVEL_MINIMAL)
		ereport(ERROR,
				(errmsg("WAL streaming (max_wal_senders > 0) requires wal_level \"archive\", \"hot_standby\" or \"logical\"")));

	/*
	 * Other one-time internal sanity checks can go here, if they are fast.
	 * (Put any slow processing further down, after postmaster.pid creation.)
	 */
	if (!CheckDateTokenTables())
	{
		write_stderr("%s: invalid datetoken tables, please fix\n", progname);
		ExitPostmaster(1);
	}

	/*
	 * Now that we are done processing the postmaster arguments, reset
	 * getopt(3) library so that it will work correctly in subprocesses.
	 */
	optind = 1;
#ifdef HAVE_INT_OPTRESET
	optreset = 1;				/* some systems need this too */
#endif

	/* For debugging: display postmaster environment */
	{
		extern char **environ;
		char	  **p;

		ereport(DEBUG3,
			(errmsg_internal("%s: PostmasterMain: initial environment dump:",
							 progname)));
		ereport(DEBUG3,
			 (errmsg_internal("-----------------------------------------")));
		for (p = environ; *p; ++p)
			ereport(DEBUG3,
					(errmsg_internal("\t%s", *p)));
		ereport(DEBUG3,
			 (errmsg_internal("-----------------------------------------")));
	}

	/*
	 * Create lockfile for data directory.
	 *
	 * We want to do this before we try to grab the input sockets, because the
	 * data directory interlock is more reliable than the socket-file
	 * interlock (thanks to whoever decided to put socket files in /tmp :-().
	 * For the same reason, it's best to grab the TCP socket(s) before the
	 * Unix socket(s).
	 */
	CreateDataDirLockFile(true);

	/*
	 * Initialize SSL library, if specified.
	 */
#ifdef USE_SSL
	if (EnableSSL)
		secure_initialize();
#endif

	/*
	 * process any libraries that should be preloaded at postmaster start
	 */
	process_shared_preload_libraries();

	/*
	 * Now that loadable modules have had their chance to register background
	 * workers, calculate MaxBackends.
	 */
	InitializeMaxBackends();

	/*
	 * Establish input sockets.
	 */
	for (i = 0; i < MAXLISTEN; i++)
		ListenSocket[i] = PGINVALID_SOCKET;

	if (ListenAddresses)
	{
		char	   *rawstring;
		List	   *elemlist;
		ListCell   *l;
		int			success = 0;

		/* Need a modifiable copy of ListenAddresses */
		rawstring = pstrdup(ListenAddresses);

		/* Parse string into list of hostnames */
		if (!SplitIdentifierString(rawstring, ',', &elemlist))
		{
			/* syntax error in list */
			ereport(FATAL,
					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
					 errmsg("invalid list syntax in parameter \"%s\"",
							"listen_addresses")));
		}

		foreach(l, elemlist)
		{
			char	   *curhost = (char *) lfirst(l);

			if (strcmp(curhost, "*") == 0)
				status = StreamServerPort(AF_UNSPEC, NULL,
										  (unsigned short) PostPortNumber,
										  NULL,
										  ListenSocket, MAXLISTEN);
			else
				status = StreamServerPort(AF_UNSPEC, curhost,
										  (unsigned short) PostPortNumber,
										  NULL,
										  ListenSocket, MAXLISTEN);

			if (status == STATUS_OK)
			{
				success++;
				/* record the first successful host addr in lockfile */
				if (!listen_addr_saved)
				{
					AddToDataDirLockFile(LOCK_FILE_LINE_LISTEN_ADDR, curhost);
					listen_addr_saved = true;
				}
			}
			else
				ereport(WARNING,
						(errmsg("could not create listen socket for \"%s\"",
								curhost)));
		}

		if (!success && elemlist != NIL)
			ereport(FATAL,
					(errmsg("could not create any TCP/IP sockets")));

		list_free(elemlist);
		pfree(rawstring);
	}

#ifdef USE_BONJOUR
	/* Register for Bonjour only if we opened TCP socket(s) */
	if (enable_bonjour && ListenSocket[0] != PGINVALID_SOCKET)
	{
		DNSServiceErrorType err;

		/*
		 * We pass 0 for interface_index, which will result in registering on
		 * all "applicable" interfaces.  It's not entirely clear from the
		 * DNS-SD docs whether this would be appropriate if we have bound to
		 * just a subset of the available network interfaces.
		 */
		err = DNSServiceRegister(&bonjour_sdref,
								 0,
								 0,
								 bonjour_name,
								 "_postgresql._tcp.",
								 NULL,
								 NULL,
								 htons(PostPortNumber),
								 0,
								 NULL,
								 NULL,
								 NULL);
		if (err != kDNSServiceErr_NoError)
			elog(LOG, "DNSServiceRegister() failed: error code %ld",
				 (long) err);

		/*
		 * We don't bother to read the mDNS daemon's reply, and we expect that
		 * it will automatically terminate our registration when the socket is
		 * closed at postmaster termination.  So there's nothing more to be
		 * done here.  However, the bonjour_sdref is kept around so that
		 * forked children can close their copies of the socket.
		 */
	}
#endif

#ifdef HAVE_UNIX_SOCKETS
	if (Unix_socket_directories)
	{
		char	   *rawstring;
		List	   *elemlist;
		ListCell   *l;
		int			success = 0;

		/* Need a modifiable copy of Unix_socket_directories */
		rawstring = pstrdup(Unix_socket_directories);

		/* Parse string into list of directories */
		if (!SplitDirectoriesString(rawstring, ',', &elemlist))
		{
			/* syntax error in list */
			ereport(FATAL,
					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
					 errmsg("invalid list syntax in parameter \"%s\"",
							"unix_socket_directories")));
		}

		foreach(l, elemlist)
		{
			char	   *socketdir = (char *) lfirst(l);

			status = StreamServerPort(AF_UNIX, NULL,
									  (unsigned short) PostPortNumber,
									  socketdir,
									  ListenSocket, MAXLISTEN);

			if (status == STATUS_OK)
			{
				success++;
				/* record the first successful Unix socket in lockfile */
				if (success == 1)
					AddToDataDirLockFile(LOCK_FILE_LINE_SOCKET_DIR, socketdir);
			}
			else
				ereport(WARNING,
						(errmsg("could not create Unix-domain socket in directory \"%s\"",
								socketdir)));
		}

		if (!success && elemlist != NIL)
			ereport(FATAL,
					(errmsg("could not create any Unix-domain sockets")));

		list_free_deep(elemlist);
		pfree(rawstring);
	}
#endif

	/*
	 * check that we have some socket to listen on
	 */
	if (ListenSocket[0] == PGINVALID_SOCKET)
		ereport(FATAL,
				(errmsg("no socket created for listening")));

	/*
	 * If no valid TCP ports, write an empty line for listen address,
	 * indicating the Unix socket must be used.  Note that this line is not
	 * added to the lock file until there is a socket backing it.
	 */
	if (!listen_addr_saved)
		AddToDataDirLockFile(LOCK_FILE_LINE_LISTEN_ADDR, "");

	/*
	 * Set up shared memory and semaphores.
	 */
	reset_shared(PostPortNumber);

	/*
	 * Estimate number of openable files.  This must happen after setting up
	 * semaphores, because on some platforms semaphores count as open files.
	 */
	set_max_safe_fds();

	/*
	 * Set reference point for stack-depth checking.
	 */
	set_stack_base();

	/*
	 * Initialize pipe (or process handle on Windows) that allows children to
	 * wake up from sleep on postmaster death.
	 */
	InitPostmasterDeathWatchHandle();

#ifdef WIN32

	/*
	 * Initialize I/O completion port used to deliver list of dead children.
	 */
	win32ChildQueue = CreateIoCompletionPort(INVALID_HANDLE_VALUE, NULL, 0, 1);
	if (win32ChildQueue == NULL)
		ereport(FATAL,
		   (errmsg("could not create I/O completion port for child queue")));
#endif

	/*
	 * Record postmaster options.  We delay this till now to avoid recording
	 * bogus options (eg, NBuffers too high for available memory).
	 */
	if (!CreateOptsFile(argc, argv, my_exec_path))
		ExitPostmaster(1);

#ifdef EXEC_BACKEND
	/* Write out nondefault GUC settings for child processes to use */
	write_nondefault_variables(PGC_POSTMASTER);
#endif

	/*
	 * Write the external PID file if requested
	 */
	if (external_pid_file)
	{
		FILE	   *fpidfile = fopen(external_pid_file, "w");

		if (fpidfile)
		{
			fprintf(fpidfile, "%d\n", MyProcPid);
			fclose(fpidfile);

			/* Make PID file world readable */
			if (chmod(external_pid_file, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH) != 0)
				write_stderr("%s: could not change permissions of external PID file \"%s\": %s\n",
							 progname, external_pid_file, strerror(errno));
		}
		else
			write_stderr("%s: could not write external PID file \"%s\": %s\n",
						 progname, external_pid_file, strerror(errno));

		on_proc_exit(unlink_external_pid_file, 0);
	}

	/*
	 * If enabled, start up syslogger collection subprocess
	 */
	SysLoggerPID = SysLogger_Start();

	/*
	 * Reset whereToSendOutput from DestDebug (its starting state) to
	 * DestNone. This stops ereport from sending log messages to stderr unless
	 * Log_destination permits.  We don't do this until the postmaster is
	 * fully launched, since startup failures may as well be reported to
	 * stderr.
	 *
	 * If we are in fact disabling logging to stderr, first emit a log message
	 * saying so, to provide a breadcrumb trail for users who may not remember
	 * that their logging is configured to go somewhere else.
	 */
	if (!(Log_destination & LOG_DESTINATION_STDERR))
		ereport(LOG,
				(errmsg("ending log output to stderr"),
			  errhint("Future log output will go to log destination \"%s\".",
					  Log_destination_string)));

	whereToSendOutput = DestNone;

	/*
	 * Initialize stats collection subsystem (this does NOT start the
	 * collector process!)
	 */
	pgstat_init();

	/*
	 * Initialize the autovacuum subsystem (again, no process start yet)
	 */
	autovac_init();

	/*
	 * Load configuration files for client authentication.
	 */
	if (!load_hba())
	{
		/*
		 * It makes no sense to continue if we fail to load the HBA file,
		 * since there is no way to connect to the database in this case.
		 */
		ereport(FATAL,
				(errmsg("could not load pg_hba.conf")));
	}
	if (!load_ident())
	{
		/*
		 * We can start up without the IDENT file, although it means that you
		 * cannot log in using any of the authentication methods that need a
		 * user name mapping. load_ident() already logged the details of error
		 * to the log.
		 */
	}


	/*
	 * Remove old temporary files.  At this point there can be no other
	 * Postgres processes running in this directory, so this should be safe.
	 */
	RemovePgTempFiles();

	/*
	 * Remember postmaster startup time
	 */
	PgStartTime = GetCurrentTimestamp();
	/* PostmasterRandom wants its own copy */
	gettimeofday(&random_start_time, NULL);

	/*
	 * We're ready to rock and roll...
	 */
	StartupPID = StartupDataBase();
	Assert(StartupPID != 0);
	pmState = PM_STARTUP;

	/* Some workers may be scheduled to start now */
	maybe_start_bgworker();

	status = ServerLoop();

	/*
	 * ServerLoop probably shouldn't ever return, but if it does, close down.
	 */
	ExitPostmaster(status != STATUS_OK);

	abort();					/* not reached */
}


/*
 * on_proc_exit callback to delete external_pid_file
 */
static void
unlink_external_pid_file(int status, Datum arg)
{
	if (external_pid_file)
		unlink(external_pid_file);
}


/*
 * Compute and check the directory paths to files that are part of the
 * installation (as deduced from the postgres executable's own location)
 */
static void
getInstallationPaths(const char *argv0)
{
	DIR		   *pdir;

	/* Locate the postgres executable itself */
	if (find_my_exec(argv0, my_exec_path) < 0)
		elog(FATAL, "%s: could not locate my own executable path", argv0);

#ifdef EXEC_BACKEND
	/* Locate executable backend before we change working directory */
	if (find_other_exec(argv0, "postgres", PG_BACKEND_VERSIONSTR,
						postgres_exec_path) < 0)
		ereport(FATAL,
				(errmsg("%s: could not locate matching postgres executable",
						argv0)));
#endif

	/*
	 * Locate the pkglib directory --- this has to be set early in case we try
	 * to load any modules from it in response to postgresql.conf entries.
	 */
	get_pkglib_path(my_exec_path, pkglib_path);

	/*
	 * Verify that there's a readable directory there; otherwise the Postgres
	 * installation is incomplete or corrupt.  (A typical cause of this
	 * failure is that the postgres executable has been moved or hardlinked to
	 * some directory that's not a sibling of the installation lib/
	 * directory.)
	 */
	pdir = AllocateDir(pkglib_path);
	if (pdir == NULL)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not open directory \"%s\": %m",
						pkglib_path),
				 errhint("This may indicate an incomplete PostgreSQL installation, or that the file \"%s\" has been moved away from its proper location.",
						 my_exec_path)));
	FreeDir(pdir);

	/*
	 * XXX is it worth similarly checking the share/ directory?  If the lib/
	 * directory is there, then share/ probably is too.
	 */
}


/*
 * Validate the proposed data directory
 */
static void
checkDataDir(void)
{
	char		path[MAXPGPATH];
	FILE	   *fp;
	struct stat stat_buf;

	Assert(DataDir);

	if (stat(DataDir, &stat_buf) != 0)
	{
		if (errno == ENOENT)
			ereport(FATAL,
					(errcode_for_file_access(),
					 errmsg("data directory \"%s\" does not exist",
							DataDir)));
		else
			ereport(FATAL,
					(errcode_for_file_access(),
				 errmsg("could not read permissions of directory \"%s\": %m",
						DataDir)));
	}

	/* eventual chdir would fail anyway, but let's test ... */
	if (!S_ISDIR(stat_buf.st_mode))
		ereport(FATAL,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("specified data directory \"%s\" is not a directory",
						DataDir)));

	/*
	 * Check that the directory belongs to my userid; if not, reject.
	 *
	 * 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);
}

/*
 * Determine how long should we let ServerLoop sleep.
 *
 * In normal conditions we wait at most one minute, to ensure that the other
 * background tasks handled by ServerLoop get done even when no requests are
 * arriving.  However, if there are background workers waiting to be started,
 * we don't actually sleep so that they are quickly serviced.
 */
static void
DetermineSleepTime(struct timeval * timeout)
{
	TimestampTz next_wakeup = 0;

	/*
	 * Normal case: either there are no background workers at all, or we're in
	 * a shutdown sequence (during which we ignore bgworkers altogether).
	 */
	if (Shutdown > NoShutdown ||
		(!StartWorkerNeeded && !HaveCrashedWorker))
	{
		if (AbortStartTime > 0)
		{
			/* time left to abort; clamp to 0 in case it already expired */
			timeout->tv_sec = Max(SIGKILL_CHILDREN_AFTER_SECS -
								  (time(NULL) - AbortStartTime), 0);
			timeout->tv_usec = 0;
		}
		else
		{
			timeout->tv_sec = 60;
			timeout->tv_usec = 0;
		}
		return;
	}

	if (StartWorkerNeeded)
	{
		timeout->tv_sec = 0;
		timeout->tv_usec = 0;
		return;
	}

	if (HaveCrashedWorker)
	{
		slist_mutable_iter siter;

		/*
		 * When there are crashed bgworkers, we sleep just long enough that
		 * they are restarted when they request to be.  Scan the list to
		 * determine the minimum of all wakeup times according to most recent
		 * crash time and requested restart interval.
		 */
		slist_foreach_modify(siter, &BackgroundWorkerList)
		{
			RegisteredBgWorker *rw;
			TimestampTz this_wakeup;

			rw = slist_container(RegisteredBgWorker, rw_lnode, siter.cur);

			if (rw->rw_crashed_at == 0)
				continue;

			if (rw->rw_worker.bgw_restart_time == BGW_NEVER_RESTART
				|| rw->rw_terminate)
			{
				ForgetBackgroundWorker(&siter);
				continue;
			}

			this_wakeup = TimestampTzPlusMilliseconds(rw->rw_crashed_at,
									 1000L * rw->rw_worker.bgw_restart_time);
			if (next_wakeup == 0 || this_wakeup < next_wakeup)
				next_wakeup = this_wakeup;
		}
	}

	if (next_wakeup != 0)
	{
		long		secs;
		int			microsecs;

		TimestampDifference(GetCurrentTimestamp(), next_wakeup,
							&secs, &microsecs);
		timeout->tv_sec = secs;
		timeout->tv_usec = microsecs;

		/* Ensure we don't exceed one minute */
		if (timeout->tv_sec > 60)
		{
			timeout->tv_sec = 60;
			timeout->tv_usec = 0;
		}
	}
	else
	{
		timeout->tv_sec = 60;
		timeout->tv_usec = 0;
	}
}

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

	last_touch_time = time(NULL);

	nSockets = initMasks(&readmask);

	for (;;)
	{
		fd_set		rmask;
		int			selres;

		/*
		 * Wait for a connection request to arrive.
		 *
		 * If we are in PM_WAIT_DEAD_END state, then we don't want to accept
		 * any new connections, so we don't call select() at all; just sleep
		 * for a little bit with signals unblocked.
		 */
		memcpy((char *) &rmask, (char *) &readmask, sizeof(fd_set));

		PG_SETMASK(&UnBlockSig);

		if (pmState == PM_WAIT_DEAD_END)
		{
			pg_usleep(100000L); /* 100 msec seems reasonable */
			selres = 0;
		}
		else
		{
			/* must set timeout each time; some OSes change it! */
			struct timeval timeout;

			DetermineSleepTime(&timeout);

			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);

		/* Now check the select() result */
		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)
		{
			int			i;

			for (i = 0; i < MAXLISTEN; i++)
			{
				if (ListenSocket[i] == PGINVALID_SOCKET)
					break;
				if (FD_ISSET(ListenSocket[i], &rmask))
				{
					Port	   *port;

					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 log collector, try to start a new one */
		if (SysLoggerPID == 0 && Logging_collector)
			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.  Likewise for the checkpointer.
		 */
		if (pmState == PM_RUN || pmState == PM_RECOVERY ||
			pmState == PM_HOT_STANDBY)
		{
			if (CheckpointerPID == 0)
				CheckpointerPID = StartCheckpointer();
			if (BgWriterPID == 0)
				BgWriterPID = StartBackgroundWriter();
		}

		/*
		 * Likewise, if we have lost the walwriter process, try to start a new
		 * one.  But this is needed only in normal operation (else we cannot
		 * be writing any new WAL).
		 */
		if (WalWriterPID == 0 && pmState == PM_RUN)
			WalWriterPID = StartWalWriter();

		/*
		 * If we have lost the autovacuum launcher, try to start a new one. We
		 * don't want autovacuum to run in binary upgrade mode because
		 * autovacuum might update relfrozenxid for empty tables before the
		 * physical files are put in place.
		 */
		if (!IsBinaryUpgrade && AutoVacPID == 0 &&
			(AutoVacuumingActive() || start_autovac_launcher) &&
			pmState == PM_RUN)
		{
			AutoVacPID = StartAutoVacLauncher();
			if (AutoVacPID != 0)
				start_autovac_launcher = false; /* signal processed */
		}

		/* If we have lost the archiver, try to start a new one */
		if (XLogArchivingActive() && PgArchPID == 0 && pmState == PM_RUN)
			PgArchPID = pgarch_start();

		/* If we have lost the stats collector, try to start a new one */
		if (PgStatPID == 0 && pmState == PM_RUN)
			PgStatPID = pgstat_start();

		/* If we need to signal the autovacuum launcher, do so now */
		if (avlauncher_needs_signal)
		{
			avlauncher_needs_signal = false;
			if (AutoVacPID != 0)
				kill(AutoVacPID, SIGUSR2);
		}

		/* Get other worker processes running, if needed */
		if (StartWorkerNeeded || HaveCrashedWorker)
			maybe_start_bgworker();

		/*
		 * Touch Unix socket and lock files 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)
		{
			TouchSocketFiles();
			TouchSocketLockFiles();
			last_touch_time = now;
		}

		/*
		 * If we already sent SIGQUIT to children and they are slow to shut
		 * down, it's time to send them SIGKILL.  This doesn't happen
		 * normally, but under certain conditions backends can get stuck while
		 * shutting down.  This is a last measure to get them unwedged.
		 *
		 * Note we also do this during recovery from a process crash.
		 */
		if ((Shutdown >= ImmediateShutdown || (FatalError && !SendStop)) &&
			AbortStartTime > 0 &&
			now - AbortStartTime >= SIGKILL_CHILDREN_AFTER_SECS)
		{
			/* We were gentle with them before. Not anymore */
			TerminateChildren(SIGKILL);
			/* reset flag so we don't SIGKILL again */
			AbortStartTime = 0;

			/*
			 * Additionally, unless we're recovering from a process crash,
			 * it's now the time for postmaster to abandon ship.
			 */
			if (!FatalError)
				ExitPostmaster(1);
		}
	}
}

/*
 * 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			maxsock = -1;
	int			i;

	FD_ZERO(rmask);

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

		if (fd == PGINVALID_SOCKET)
			break;
		FD_SET(fd, rmask);

		if (fd > maxsock)
			maxsock = fd;
	}

	return maxsock + 1;
}


/*
 * Read a client's 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;…

Large files files are truncated, but you can click here to view the full file