/src/postgres/src/backend/postmaster/postmaster.c
Line | Count | Source |
1 | | /*------------------------------------------------------------------------- |
2 | | * |
3 | | * postmaster.c |
4 | | * This program acts as a clearing house for requests to the |
5 | | * POSTGRES system. Frontend programs connect to the Postmaster, |
6 | | * and postmaster forks a new backend process to handle the |
7 | | * connection. |
8 | | * |
9 | | * The postmaster also manages system-wide operations such as |
10 | | * startup and shutdown. The postmaster itself doesn't do those |
11 | | * operations, mind you --- it just forks off a subprocess to do them |
12 | | * at the right times. It also takes care of resetting the system |
13 | | * if a backend crashes. |
14 | | * |
15 | | * The postmaster process creates the shared memory and semaphore |
16 | | * pools during startup, but as a rule does not touch them itself. |
17 | | * In particular, it is not a member of the PGPROC array of backends |
18 | | * and so it cannot participate in lock-manager operations. Keeping |
19 | | * the postmaster away from shared memory operations makes it simpler |
20 | | * and more reliable. The postmaster is almost always able to recover |
21 | | * from crashes of individual backends by resetting shared memory; |
22 | | * if it did much with shared memory then it would be prone to crashing |
23 | | * along with the backends. |
24 | | * |
25 | | * When a request message is received, we now fork() immediately. |
26 | | * The child process performs authentication of the request, and |
27 | | * then becomes a backend if successful. This allows the auth code |
28 | | * to be written in a simple single-threaded style (as opposed to the |
29 | | * crufty "poor man's multitasking" code that used to be needed). |
30 | | * More importantly, it ensures that blockages in non-multithreaded |
31 | | * libraries like SSL or PAM cannot cause denial of service to other |
32 | | * clients. |
33 | | * |
34 | | * |
35 | | * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group |
36 | | * Portions Copyright (c) 1994, Regents of the University of California |
37 | | * |
38 | | * |
39 | | * IDENTIFICATION |
40 | | * src/backend/postmaster/postmaster.c |
41 | | * |
42 | | * NOTES |
43 | | * |
44 | | * Initialization: |
45 | | * The Postmaster sets up shared memory data structures |
46 | | * for the backends. |
47 | | * |
48 | | * Synchronization: |
49 | | * The Postmaster shares memory with the backends but should avoid |
50 | | * touching shared memory, so as not to become stuck if a crashing |
51 | | * backend screws up locks or shared memory. Likewise, the Postmaster |
52 | | * should never block on messages from frontend clients. |
53 | | * |
54 | | * Garbage Collection: |
55 | | * The Postmaster cleans up after backends if they have an emergency |
56 | | * exit and/or core dump. |
57 | | * |
58 | | * Error Reporting: |
59 | | * Use write_stderr() only for reporting "interactive" errors |
60 | | * (essentially, bogus arguments on the command line). Once the |
61 | | * postmaster is launched, use ereport(). |
62 | | * |
63 | | *------------------------------------------------------------------------- |
64 | | */ |
65 | | |
66 | | #include "postgres.h" |
67 | | |
68 | | #include <unistd.h> |
69 | | #include <signal.h> |
70 | | #include <time.h> |
71 | | #include <sys/wait.h> |
72 | | #include <ctype.h> |
73 | | #include <sys/stat.h> |
74 | | #include <sys/socket.h> |
75 | | #include <fcntl.h> |
76 | | #include <sys/param.h> |
77 | | #include <netdb.h> |
78 | | #include <limits.h> |
79 | | |
80 | | #ifdef USE_BONJOUR |
81 | | #include <dns_sd.h> |
82 | | #endif |
83 | | |
84 | | #ifdef USE_SYSTEMD |
85 | | #include <systemd/sd-daemon.h> |
86 | | #endif |
87 | | |
88 | | #ifdef HAVE_PTHREAD_IS_THREADED_NP |
89 | | #include <pthread.h> |
90 | | #endif |
91 | | |
92 | | #include "access/xlog.h" |
93 | | #include "access/xlog_internal.h" |
94 | | #include "access/xlogrecovery.h" |
95 | | #include "common/file_perm.h" |
96 | | #include "common/pg_prng.h" |
97 | | #include "lib/ilist.h" |
98 | | #include "libpq/libpq.h" |
99 | | #include "libpq/pqsignal.h" |
100 | | #include "pgstat.h" |
101 | | #include "port/pg_bswap.h" |
102 | | #include "port/pg_getopt_ctx.h" |
103 | | #include "postmaster/autovacuum.h" |
104 | | #include "postmaster/bgworker_internals.h" |
105 | | #include "postmaster/pgarch.h" |
106 | | #include "postmaster/postmaster.h" |
107 | | #include "postmaster/syslogger.h" |
108 | | #include "postmaster/walsummarizer.h" |
109 | | #include "replication/logicallauncher.h" |
110 | | #include "replication/slotsync.h" |
111 | | #include "replication/walsender.h" |
112 | | #include "storage/aio_subsys.h" |
113 | | #include "storage/fd.h" |
114 | | #include "storage/io_worker.h" |
115 | | #include "storage/ipc.h" |
116 | | #include "storage/pmsignal.h" |
117 | | #include "storage/proc.h" |
118 | | #include "storage/shmem_internal.h" |
119 | | #include "tcop/backend_startup.h" |
120 | | #include "tcop/tcopprot.h" |
121 | | #include "utils/datetime.h" |
122 | | #include "utils/memutils.h" |
123 | | #include "utils/pidfile.h" |
124 | | #include "utils/timestamp.h" |
125 | | #include "utils/varlena.h" |
126 | | |
127 | | #ifdef EXEC_BACKEND |
128 | | #include "common/file_utils.h" |
129 | | #include "storage/pg_shmem.h" |
130 | | #endif |
131 | | |
132 | | |
133 | | /* |
134 | | * CountChildren and SignalChildren take a bitmask argument to represent |
135 | | * BackendTypes to count or signal. Define a separate type and functions to |
136 | | * work with the bitmasks, to avoid accidentally passing a plain BackendType |
137 | | * in place of a bitmask or vice versa. |
138 | | */ |
139 | | typedef struct |
140 | | { |
141 | | uint32 mask; |
142 | | } BackendTypeMask; |
143 | | |
144 | | StaticAssertDecl(BACKEND_NUM_TYPES < 32, "too many backend types for uint32"); |
145 | | |
146 | | static const BackendTypeMask BTYPE_MASK_ALL = {(1 << BACKEND_NUM_TYPES) - 1}; |
147 | | static const BackendTypeMask BTYPE_MASK_NONE = {0}; |
148 | | |
149 | | static inline BackendTypeMask |
150 | | btmask(BackendType t) |
151 | 0 | { |
152 | 0 | BackendTypeMask mask = {.mask = 1 << t}; |
153 | |
|
154 | 0 | return mask; |
155 | 0 | } |
156 | | |
157 | | static inline BackendTypeMask |
158 | | btmask_add_n(BackendTypeMask mask, int nargs, BackendType *t) |
159 | 0 | { |
160 | 0 | for (int i = 0; i < nargs; i++) |
161 | 0 | mask.mask |= 1 << t[i]; |
162 | 0 | return mask; |
163 | 0 | } |
164 | | |
165 | | #define btmask_add(mask, ...) \ |
166 | 0 | btmask_add_n(mask, \ |
167 | 0 | lengthof(((BackendType[]){__VA_ARGS__})), \ |
168 | 0 | (BackendType[]){__VA_ARGS__} \ |
169 | 0 | ) |
170 | | |
171 | | static inline BackendTypeMask |
172 | | btmask_del(BackendTypeMask mask, BackendType t) |
173 | 0 | { |
174 | 0 | mask.mask &= ~(1 << t); |
175 | 0 | return mask; |
176 | 0 | } |
177 | | |
178 | | static inline BackendTypeMask |
179 | | btmask_all_except_n(int nargs, BackendType *t) |
180 | 0 | { |
181 | 0 | BackendTypeMask mask = BTYPE_MASK_ALL; |
182 | |
|
183 | 0 | for (int i = 0; i < nargs; i++) |
184 | 0 | mask = btmask_del(mask, t[i]); |
185 | 0 | return mask; |
186 | 0 | } |
187 | | |
188 | | #define btmask_all_except(...) \ |
189 | 0 | btmask_all_except_n( \ |
190 | 0 | lengthof(((BackendType[]){__VA_ARGS__})), \ |
191 | 0 | (BackendType[]){__VA_ARGS__} \ |
192 | 0 | ) |
193 | | |
194 | | static inline bool |
195 | | btmask_contains(BackendTypeMask mask, BackendType t) |
196 | 0 | { |
197 | 0 | return (mask.mask & (1 << t)) != 0; |
198 | 0 | } |
199 | | |
200 | | |
201 | | BackgroundWorker *MyBgworkerEntry = NULL; |
202 | | |
203 | | /* The socket number we are listening for connections on */ |
204 | | int PostPortNumber = DEF_PGPORT; |
205 | | |
206 | | /* The directory names for Unix socket(s) */ |
207 | | char *Unix_socket_directories; |
208 | | |
209 | | /* The TCP listen address(es) */ |
210 | | char *ListenAddresses; |
211 | | |
212 | | /* |
213 | | * SuperuserReservedConnections is the number of backends reserved for |
214 | | * superuser use, and ReservedConnections is the number of backends reserved |
215 | | * for use by roles with privileges of the pg_use_reserved_connections |
216 | | * predefined role. These are taken out of the pool of MaxConnections backend |
217 | | * slots, so the number of backend slots available for roles that are neither |
218 | | * superuser nor have privileges of pg_use_reserved_connections is |
219 | | * (MaxConnections - SuperuserReservedConnections - ReservedConnections). |
220 | | * |
221 | | * If the number of remaining slots is less than or equal to |
222 | | * SuperuserReservedConnections, only superusers can make new connections. If |
223 | | * the number of remaining slots is greater than SuperuserReservedConnections |
224 | | * but less than or equal to |
225 | | * (SuperuserReservedConnections + ReservedConnections), only superusers and |
226 | | * roles with privileges of pg_use_reserved_connections can make new |
227 | | * connections. Note that pre-existing superuser and |
228 | | * pg_use_reserved_connections connections don't count against the limits. |
229 | | */ |
230 | | int SuperuserReservedConnections; |
231 | | int ReservedConnections; |
232 | | |
233 | | /* The socket(s) we're listening to. */ |
234 | 0 | #define MAXLISTEN 64 |
235 | | static int NumListenSockets = 0; |
236 | | static pgsocket *ListenSockets = NULL; |
237 | | |
238 | | /* still more option variables */ |
239 | | bool EnableSSL = false; |
240 | | |
241 | | int PreAuthDelay = 0; |
242 | | int AuthenticationTimeout = 60; |
243 | | |
244 | | bool log_hostname; /* for ps display and logging */ |
245 | | |
246 | | bool enable_bonjour = false; |
247 | | char *bonjour_name; |
248 | | bool restart_after_crash = true; |
249 | | bool remove_temp_files_after_crash = true; |
250 | | |
251 | | /* |
252 | | * When terminating child processes after fatal errors, like a crash of a |
253 | | * child process, we normally send SIGQUIT -- and most other comments in this |
254 | | * file are written on the assumption that we do -- but developers might |
255 | | * prefer to use SIGABRT to collect per-child core dumps. |
256 | | */ |
257 | | bool send_abort_for_crash = false; |
258 | | bool send_abort_for_kill = false; |
259 | | |
260 | | /* special child processes; NULL when not running */ |
261 | | static PMChild *StartupPMChild = NULL, |
262 | | *BgWriterPMChild = NULL, |
263 | | *CheckpointerPMChild = NULL, |
264 | | *WalWriterPMChild = NULL, |
265 | | *WalReceiverPMChild = NULL, |
266 | | *WalSummarizerPMChild = NULL, |
267 | | *AutoVacLauncherPMChild = NULL, |
268 | | *PgArchPMChild = NULL, |
269 | | *SysLoggerPMChild = NULL, |
270 | | *SlotSyncWorkerPMChild = NULL; |
271 | | |
272 | | /* Startup process's status */ |
273 | | typedef enum |
274 | | { |
275 | | STARTUP_NOT_RUNNING, |
276 | | STARTUP_RUNNING, |
277 | | STARTUP_SIGNALED, /* we sent it a SIGQUIT or SIGKILL */ |
278 | | STARTUP_CRASHED, |
279 | | } StartupStatusEnum; |
280 | | |
281 | | static StartupStatusEnum StartupStatus = STARTUP_NOT_RUNNING; |
282 | | |
283 | | /* Startup/shutdown state */ |
284 | 0 | #define NoShutdown 0 |
285 | 0 | #define SmartShutdown 1 |
286 | | #define FastShutdown 2 |
287 | 0 | #define ImmediateShutdown 3 |
288 | | |
289 | | static int Shutdown = NoShutdown; |
290 | | |
291 | | static bool FatalError = false; /* T if recovering from backend crash */ |
292 | | |
293 | | /* |
294 | | * We use a simple state machine to control startup, shutdown, and |
295 | | * crash recovery (which is rather like shutdown followed by startup). |
296 | | * |
297 | | * After doing all the postmaster initialization work, we enter PM_STARTUP |
298 | | * state and the startup process is launched. The startup process begins by |
299 | | * reading the control file and other preliminary initialization steps. |
300 | | * In a normal startup, or after crash recovery, the startup process exits |
301 | | * with exit code 0 and we switch to PM_RUN state. However, archive recovery |
302 | | * is handled specially since it takes much longer and we would like to support |
303 | | * hot standby during archive recovery. |
304 | | * |
305 | | * When the startup process is ready to start archive recovery, it signals the |
306 | | * postmaster, and we switch to PM_RECOVERY state. The background writer and |
307 | | * checkpointer are already running (as these are launched during PM_STARTUP), |
308 | | * and the startup process continues applying WAL. If Hot Standby is enabled, |
309 | | * then, after reaching a consistent point in WAL redo, startup process |
310 | | * signals us again, and we switch to PM_HOT_STANDBY state and begin accepting |
311 | | * connections to perform read-only queries. When archive recovery is |
312 | | * finished, the startup process exits with exit code 0 and we switch to |
313 | | * PM_RUN state. |
314 | | * |
315 | | * Normal child backends can only be launched when we are in PM_RUN or |
316 | | * PM_HOT_STANDBY state. (connsAllowed can also restrict launching.) |
317 | | * In other states we handle connection requests by launching "dead-end" |
318 | | * child processes, which will simply send the client an error message and |
319 | | * quit. (We track these in the ActiveChildList so that we can know when they |
320 | | * are all gone; this is important because they're still connected to shared |
321 | | * memory, and would interfere with an attempt to destroy the shmem segment, |
322 | | * possibly leading to SHMALL failure when we try to make a new one.) |
323 | | * In PM_WAIT_DEAD_END state we are waiting for all the dead-end children |
324 | | * to drain out of the system, and therefore stop accepting connection |
325 | | * requests at all until the last existing child has quit (which hopefully |
326 | | * will not be very long). |
327 | | * |
328 | | * Notice that this state variable does not distinguish *why* we entered |
329 | | * states later than PM_RUN --- Shutdown and FatalError must be consulted |
330 | | * to find that out. FatalError is never true in PM_RECOVERY, PM_HOT_STANDBY, |
331 | | * or PM_RUN states, nor in PM_WAIT_XLOG_SHUTDOWN states (because we don't |
332 | | * enter those states when trying to recover from a crash). It can be true in |
333 | | * PM_STARTUP state, because we don't clear it until we've successfully |
334 | | * started WAL redo. |
335 | | */ |
336 | | typedef enum |
337 | | { |
338 | | PM_INIT, /* postmaster starting */ |
339 | | PM_STARTUP, /* waiting for startup subprocess */ |
340 | | PM_RECOVERY, /* in archive recovery mode */ |
341 | | PM_HOT_STANDBY, /* in hot standby mode */ |
342 | | PM_RUN, /* normal "database is alive" state */ |
343 | | PM_STOP_BACKENDS, /* need to stop remaining backends */ |
344 | | PM_WAIT_BACKENDS, /* waiting for live backends to exit */ |
345 | | PM_WAIT_XLOG_SHUTDOWN, /* waiting for checkpointer to do shutdown |
346 | | * ckpt */ |
347 | | PM_WAIT_XLOG_ARCHIVAL, /* waiting for archiver and walsenders to |
348 | | * finish */ |
349 | | PM_WAIT_IO_WORKERS, /* waiting for io workers to exit */ |
350 | | PM_WAIT_CHECKPOINTER, /* waiting for checkpointer to shut down */ |
351 | | PM_WAIT_DEAD_END, /* waiting for dead-end children to exit */ |
352 | | PM_NO_CHILDREN, /* all important children have exited */ |
353 | | } PMState; |
354 | | |
355 | | static PMState pmState = PM_INIT; |
356 | | |
357 | | /* |
358 | | * While performing a "smart shutdown", we restrict new connections but stay |
359 | | * in PM_RUN or PM_HOT_STANDBY state until all the client backends are gone. |
360 | | * connsAllowed is a sub-state indicator showing the active restriction. |
361 | | * It is of no interest unless pmState is PM_RUN or PM_HOT_STANDBY. |
362 | | */ |
363 | | static bool connsAllowed = true; |
364 | | |
365 | | /* Start time of SIGKILL timeout during immediate shutdown or child crash */ |
366 | | /* Zero means timeout is not running */ |
367 | | static time_t AbortStartTime = 0; |
368 | | |
369 | | /* Length of said timeout */ |
370 | 0 | #define SIGKILL_CHILDREN_AFTER_SECS 5 |
371 | | |
372 | | static bool ReachedNormalRunning = false; /* T if we've reached PM_RUN */ |
373 | | |
374 | | bool ClientAuthInProgress = false; /* T during new-client |
375 | | * authentication */ |
376 | | |
377 | | bool redirection_done = false; /* stderr redirected for syslogger? */ |
378 | | |
379 | | /* received START_AUTOVAC_LAUNCHER signal */ |
380 | | static bool start_autovac_launcher = false; |
381 | | |
382 | | /* the launcher needs to be signaled to communicate some condition */ |
383 | | static bool avlauncher_needs_signal = false; |
384 | | |
385 | | /* received START_WALRECEIVER signal */ |
386 | | static bool WalReceiverRequested = false; |
387 | | |
388 | | /* set when there's a worker that needs to be started up */ |
389 | | static bool StartWorkerNeeded = true; |
390 | | static bool HaveCrashedWorker = false; |
391 | | |
392 | | /* set when signals arrive */ |
393 | | static volatile sig_atomic_t pending_pm_pmsignal; |
394 | | static volatile sig_atomic_t pending_pm_child_exit; |
395 | | static volatile sig_atomic_t pending_pm_reload_request; |
396 | | static volatile sig_atomic_t pending_pm_shutdown_request; |
397 | | static volatile sig_atomic_t pending_pm_fast_shutdown_request; |
398 | | static volatile sig_atomic_t pending_pm_immediate_shutdown_request; |
399 | | |
400 | | /* event multiplexing object */ |
401 | | static WaitEventSet *pm_wait_set; |
402 | | |
403 | | #ifdef USE_SSL |
404 | | /* Set when and if SSL has been initialized properly */ |
405 | | bool LoadedSSL = false; |
406 | | #endif |
407 | | |
408 | | #ifdef USE_BONJOUR |
409 | | static DNSServiceRef bonjour_sdref = NULL; |
410 | | #endif |
411 | | |
412 | | /* State for IO worker management. */ |
413 | | static TimestampTz io_worker_launch_next_time = 0; |
414 | | static int io_worker_count = 0; |
415 | | static PMChild *io_worker_children[MAX_IO_WORKERS]; |
416 | | |
417 | | /* |
418 | | * postmaster.c - function prototypes |
419 | | */ |
420 | | static void CloseServerPorts(int status, Datum arg); |
421 | | static void unlink_external_pid_file(int status, Datum arg); |
422 | | static void getInstallationPaths(const char *argv0); |
423 | | static void checkControlFile(void); |
424 | | static void handle_pm_pmsignal_signal(SIGNAL_ARGS); |
425 | | static void handle_pm_child_exit_signal(SIGNAL_ARGS); |
426 | | static void handle_pm_reload_request_signal(SIGNAL_ARGS); |
427 | | static void handle_pm_shutdown_request_signal(SIGNAL_ARGS); |
428 | | static void process_pm_pmsignal(void); |
429 | | static void process_pm_child_exit(void); |
430 | | static void process_pm_reload_request(void); |
431 | | static void process_pm_shutdown_request(void); |
432 | | static void dummy_handler(SIGNAL_ARGS); |
433 | | static void CleanupBackend(PMChild *bp, int exitstatus); |
434 | | static void HandleChildCrash(int pid, int exitstatus, const char *procname); |
435 | | static void LogChildExit(int lev, const char *procname, |
436 | | int pid, int exitstatus); |
437 | | static void PostmasterStateMachine(void); |
438 | | static void UpdatePMState(PMState newState); |
439 | | |
440 | | pg_noreturn static void ExitPostmaster(int status); |
441 | | static int ServerLoop(void); |
442 | | static int BackendStartup(ClientSocket *client_sock); |
443 | | static void report_fork_failure_to_client(ClientSocket *client_sock, int errnum); |
444 | | static CAC_state canAcceptConnections(BackendType backend_type); |
445 | | static void signal_child(PMChild *pmchild, int signal); |
446 | | static bool SignalChildren(int signal, BackendTypeMask targetMask); |
447 | | static void TerminateChildren(int signal); |
448 | | static int CountChildren(BackendTypeMask targetMask); |
449 | | static void LaunchMissingBackgroundProcesses(void); |
450 | | static void maybe_start_bgworkers(void); |
451 | | static bool maybe_reap_io_worker(int pid); |
452 | | static void maybe_start_io_workers(void); |
453 | | static TimestampTz maybe_start_io_workers_scheduled_at(void); |
454 | | static bool CreateOptsFile(int argc, char *argv[], char *fullprogname); |
455 | | static PMChild *StartChildProcess(BackendType type); |
456 | | static void StartSysLogger(void); |
457 | | static void StartAutovacuumWorker(void); |
458 | | static bool StartBackgroundWorker(RegisteredBgWorker *rw); |
459 | | static void InitPostmasterDeathWatchHandle(void); |
460 | | |
461 | | #ifdef WIN32 |
462 | | #define WNOHANG 0 /* ignored, so any integer value will do */ |
463 | | |
464 | | static pid_t waitpid(pid_t pid, int *exitstatus, int options); |
465 | | static void WINAPI pgwin32_deadchild_callback(PVOID lpParameter, BOOLEAN TimerOrWaitFired); |
466 | | |
467 | | static HANDLE win32ChildQueue; |
468 | | |
469 | | typedef struct |
470 | | { |
471 | | HANDLE waitHandle; |
472 | | HANDLE procHandle; |
473 | | DWORD procId; |
474 | | } win32_deadchild_waitinfo; |
475 | | #endif /* WIN32 */ |
476 | | |
477 | | /* Macros to check exit status of a child process */ |
478 | 0 | #define EXIT_STATUS_0(st) ((st) == 0) |
479 | 0 | #define EXIT_STATUS_1(st) (WIFEXITED(st) && WEXITSTATUS(st) == 1) |
480 | 0 | #define EXIT_STATUS_3(st) (WIFEXITED(st) && WEXITSTATUS(st) == 3) |
481 | | |
482 | | #ifndef WIN32 |
483 | | /* |
484 | | * File descriptors for pipe used to monitor if postmaster is alive. |
485 | | * First is POSTMASTER_FD_WATCH, second is POSTMASTER_FD_OWN. |
486 | | */ |
487 | | int postmaster_alive_fds[2] = {-1, -1}; |
488 | | #else |
489 | | /* Process handle of postmaster used for the same purpose on Windows */ |
490 | | HANDLE PostmasterHandle; |
491 | | #endif |
492 | | |
493 | | /* |
494 | | * Postmaster main entry point |
495 | | */ |
496 | | void |
497 | | PostmasterMain(int argc, char *argv[]) |
498 | 0 | { |
499 | 0 | pg_getopt_ctx optctx; |
500 | 0 | int opt; |
501 | 0 | int status; |
502 | 0 | char *userDoption = NULL; |
503 | 0 | bool listen_addr_saved = false; |
504 | 0 | char *output_config_variable = NULL; |
505 | |
|
506 | 0 | InitProcessGlobals(); |
507 | |
|
508 | 0 | PostmasterPid = MyProcPid; |
509 | |
|
510 | 0 | IsPostmasterEnvironment = true; |
511 | | |
512 | | /* |
513 | | * Start our win32 signal implementation |
514 | | */ |
515 | | #ifdef WIN32 |
516 | | pgwin32_signal_initialize(); |
517 | | #endif |
518 | | |
519 | | /* |
520 | | * We should not be creating any files or directories before we check the |
521 | | * data directory (see checkDataDir()), but just in case set the umask to |
522 | | * the most restrictive (owner-only) permissions. |
523 | | * |
524 | | * checkDataDir() will reset the umask based on the data directory |
525 | | * permissions. |
526 | | */ |
527 | 0 | umask(PG_MODE_MASK_OWNER); |
528 | | |
529 | | /* |
530 | | * By default, palloc() requests in the postmaster will be allocated in |
531 | | * the PostmasterContext, which is space that can be recycled by backends. |
532 | | * Allocated data that needs to be available to backends should be |
533 | | * allocated in TopMemoryContext. |
534 | | */ |
535 | 0 | PostmasterContext = AllocSetContextCreate(TopMemoryContext, |
536 | 0 | "Postmaster", |
537 | 0 | ALLOCSET_DEFAULT_SIZES); |
538 | 0 | MemoryContextSwitchTo(PostmasterContext); |
539 | | |
540 | | /* Initialize paths to installation files */ |
541 | 0 | getInstallationPaths(argv[0]); |
542 | | |
543 | | /* |
544 | | * Set up signal handlers for the postmaster process. |
545 | | * |
546 | | * CAUTION: when changing this list, check for side-effects on the signal |
547 | | * handling setup of child processes. See tcop/postgres.c, |
548 | | * bootstrap/bootstrap.c, postmaster/bgwriter.c, postmaster/walwriter.c, |
549 | | * postmaster/autovacuum.c, postmaster/pgarch.c, postmaster/syslogger.c, |
550 | | * postmaster/bgworker.c and postmaster/checkpointer.c. |
551 | | */ |
552 | 0 | pqinitmask(); |
553 | 0 | sigprocmask(SIG_SETMASK, &BlockSig, NULL); |
554 | |
|
555 | 0 | pqsignal(SIGHUP, handle_pm_reload_request_signal); |
556 | 0 | pqsignal(SIGINT, handle_pm_shutdown_request_signal); |
557 | 0 | pqsignal(SIGQUIT, handle_pm_shutdown_request_signal); |
558 | 0 | pqsignal(SIGTERM, handle_pm_shutdown_request_signal); |
559 | 0 | pqsignal(SIGALRM, PG_SIG_IGN); /* ignored */ |
560 | 0 | pqsignal(SIGPIPE, PG_SIG_IGN); /* ignored */ |
561 | 0 | pqsignal(SIGUSR1, handle_pm_pmsignal_signal); |
562 | 0 | pqsignal(SIGUSR2, dummy_handler); /* unused, reserve for children */ |
563 | 0 | pqsignal(SIGCHLD, handle_pm_child_exit_signal); |
564 | | |
565 | | /* This may configure SIGURG, depending on platform. */ |
566 | 0 | InitializeWaitEventSupport(); |
567 | 0 | InitProcessLocalLatch(); |
568 | | |
569 | | /* |
570 | | * No other place in Postgres should touch SIGTTIN/SIGTTOU handling. We |
571 | | * ignore those signals in a postmaster environment, so that there is no |
572 | | * risk of a child process freezing up due to writing to stderr. But for |
573 | | * a standalone backend, their default handling is reasonable. Hence, all |
574 | | * child processes should just allow the inherited settings to stand. |
575 | | */ |
576 | 0 | #ifdef SIGTTIN |
577 | 0 | pqsignal(SIGTTIN, PG_SIG_IGN); /* ignored */ |
578 | 0 | #endif |
579 | 0 | #ifdef SIGTTOU |
580 | 0 | pqsignal(SIGTTOU, PG_SIG_IGN); /* ignored */ |
581 | 0 | #endif |
582 | | |
583 | | /* ignore SIGXFSZ, so that ulimit violations work like disk full */ |
584 | 0 | #ifdef SIGXFSZ |
585 | 0 | pqsignal(SIGXFSZ, PG_SIG_IGN); /* ignored */ |
586 | 0 | #endif |
587 | | |
588 | | /* Begin accepting signals. */ |
589 | 0 | sigprocmask(SIG_SETMASK, &UnBlockSig, NULL); |
590 | | |
591 | | /* |
592 | | * Options setup |
593 | | */ |
594 | 0 | InitializeGUCOptions(); |
595 | | |
596 | | /* |
597 | | * Parse command-line options. CAUTION: keep this in sync with |
598 | | * tcop/postgres.c (the option sets should not conflict) and with the |
599 | | * common help() function in main/main.c. |
600 | | */ |
601 | 0 | pg_getopt_start(&optctx, argc, argv, "B:bC:c:D:d:EeFf:h:ijk:lN:OPp:r:S:sTt:W:-:"); |
602 | 0 | optctx.opterr = 1; |
603 | 0 | while ((opt = pg_getopt_next(&optctx)) != -1) |
604 | 0 | { |
605 | 0 | switch (opt) |
606 | 0 | { |
607 | 0 | case 'B': |
608 | 0 | SetConfigOption("shared_buffers", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
609 | 0 | break; |
610 | | |
611 | 0 | case 'b': |
612 | | /* Undocumented flag used for binary upgrades */ |
613 | 0 | IsBinaryUpgrade = true; |
614 | 0 | break; |
615 | | |
616 | 0 | case 'C': |
617 | 0 | output_config_variable = strdup(optctx.optarg); |
618 | 0 | break; |
619 | | |
620 | 0 | case '-': |
621 | | |
622 | | /* |
623 | | * Error if the user misplaced a special must-be-first option |
624 | | * for dispatching to a subprogram. parse_dispatch_option() |
625 | | * returns DISPATCH_POSTMASTER if it doesn't find a match, so |
626 | | * error for anything else. |
627 | | */ |
628 | 0 | if (parse_dispatch_option(optctx.optarg) != DISPATCH_POSTMASTER) |
629 | 0 | ereport(ERROR, |
630 | 0 | (errcode(ERRCODE_SYNTAX_ERROR), |
631 | 0 | errmsg("--%s must be first argument", optctx.optarg))); |
632 | | |
633 | 0 | pg_fallthrough; |
634 | 0 | case 'c': |
635 | 0 | { |
636 | 0 | char *name, |
637 | 0 | *value; |
638 | |
|
639 | 0 | ParseLongOption(optctx.optarg, &name, &value); |
640 | 0 | if (!value) |
641 | 0 | { |
642 | 0 | if (opt == '-') |
643 | 0 | ereport(ERROR, |
644 | 0 | (errcode(ERRCODE_SYNTAX_ERROR), |
645 | 0 | errmsg("--%s requires a value", |
646 | 0 | optctx.optarg))); |
647 | 0 | else |
648 | 0 | ereport(ERROR, |
649 | 0 | (errcode(ERRCODE_SYNTAX_ERROR), |
650 | 0 | errmsg("-c %s requires a value", |
651 | 0 | optctx.optarg))); |
652 | 0 | } |
653 | | |
654 | 0 | SetConfigOption(name, value, PGC_POSTMASTER, PGC_S_ARGV); |
655 | 0 | pfree(name); |
656 | 0 | pfree(value); |
657 | 0 | break; |
658 | 0 | } |
659 | | |
660 | 0 | case 'D': |
661 | 0 | userDoption = strdup(optctx.optarg); |
662 | 0 | break; |
663 | | |
664 | 0 | case 'd': |
665 | 0 | set_debug_options(atoi(optctx.optarg), PGC_POSTMASTER, PGC_S_ARGV); |
666 | 0 | break; |
667 | | |
668 | 0 | case 'E': |
669 | 0 | SetConfigOption("log_statement", "all", PGC_POSTMASTER, PGC_S_ARGV); |
670 | 0 | break; |
671 | | |
672 | 0 | case 'e': |
673 | 0 | SetConfigOption("datestyle", "euro", PGC_POSTMASTER, PGC_S_ARGV); |
674 | 0 | break; |
675 | | |
676 | 0 | case 'F': |
677 | 0 | SetConfigOption("fsync", "false", PGC_POSTMASTER, PGC_S_ARGV); |
678 | 0 | break; |
679 | | |
680 | 0 | case 'f': |
681 | 0 | if (!set_plan_disabling_options(optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV)) |
682 | 0 | { |
683 | 0 | write_stderr("%s: invalid argument for option -f: \"%s\"\n", |
684 | 0 | progname, optctx.optarg); |
685 | 0 | ExitPostmaster(1); |
686 | 0 | } |
687 | 0 | break; |
688 | | |
689 | 0 | case 'h': |
690 | 0 | SetConfigOption("listen_addresses", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
691 | 0 | break; |
692 | | |
693 | 0 | case 'i': |
694 | 0 | SetConfigOption("listen_addresses", "*", PGC_POSTMASTER, PGC_S_ARGV); |
695 | 0 | break; |
696 | | |
697 | 0 | case 'j': |
698 | | /* only used by interactive backend */ |
699 | 0 | break; |
700 | | |
701 | 0 | case 'k': |
702 | 0 | SetConfigOption("unix_socket_directories", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
703 | 0 | break; |
704 | | |
705 | 0 | case 'l': |
706 | 0 | SetConfigOption("ssl", "true", PGC_POSTMASTER, PGC_S_ARGV); |
707 | 0 | break; |
708 | | |
709 | 0 | case 'N': |
710 | 0 | SetConfigOption("max_connections", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
711 | 0 | break; |
712 | | |
713 | 0 | case 'O': |
714 | 0 | SetConfigOption("allow_system_table_mods", "true", PGC_POSTMASTER, PGC_S_ARGV); |
715 | 0 | break; |
716 | | |
717 | 0 | case 'P': |
718 | 0 | SetConfigOption("ignore_system_indexes", "true", PGC_POSTMASTER, PGC_S_ARGV); |
719 | 0 | break; |
720 | | |
721 | 0 | case 'p': |
722 | 0 | SetConfigOption("port", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
723 | 0 | break; |
724 | | |
725 | 0 | case 'r': |
726 | | /* only used by single-user backend */ |
727 | 0 | break; |
728 | | |
729 | 0 | case 'S': |
730 | 0 | SetConfigOption("work_mem", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
731 | 0 | break; |
732 | | |
733 | 0 | case 's': |
734 | 0 | SetConfigOption("log_statement_stats", "true", PGC_POSTMASTER, PGC_S_ARGV); |
735 | 0 | break; |
736 | | |
737 | 0 | case 'T': |
738 | | |
739 | | /* |
740 | | * This option used to be defined as sending SIGSTOP after a |
741 | | * backend crash, but sending SIGABRT seems more useful. |
742 | | */ |
743 | 0 | SetConfigOption("send_abort_for_crash", "true", PGC_POSTMASTER, PGC_S_ARGV); |
744 | 0 | break; |
745 | | |
746 | 0 | case 't': |
747 | 0 | { |
748 | 0 | const char *tmp = get_stats_option_name(optctx.optarg); |
749 | |
|
750 | 0 | if (tmp) |
751 | 0 | { |
752 | 0 | SetConfigOption(tmp, "true", PGC_POSTMASTER, PGC_S_ARGV); |
753 | 0 | } |
754 | 0 | else |
755 | 0 | { |
756 | 0 | write_stderr("%s: invalid argument for option -t: \"%s\"\n", |
757 | 0 | progname, optctx.optarg); |
758 | 0 | ExitPostmaster(1); |
759 | 0 | } |
760 | 0 | break; |
761 | 0 | } |
762 | | |
763 | 0 | case 'W': |
764 | 0 | SetConfigOption("post_auth_delay", optctx.optarg, PGC_POSTMASTER, PGC_S_ARGV); |
765 | 0 | break; |
766 | | |
767 | 0 | default: |
768 | 0 | write_stderr("Try \"%s --help\" for more information.\n", |
769 | 0 | progname); |
770 | 0 | ExitPostmaster(1); |
771 | 0 | } |
772 | 0 | } |
773 | | |
774 | | /* |
775 | | * Postmaster accepts no non-option switch arguments. |
776 | | */ |
777 | 0 | if (optctx.optind < argc) |
778 | 0 | { |
779 | 0 | write_stderr("%s: invalid argument: \"%s\"\n", |
780 | 0 | progname, argv[optctx.optind]); |
781 | 0 | write_stderr("Try \"%s --help\" for more information.\n", |
782 | 0 | progname); |
783 | 0 | ExitPostmaster(1); |
784 | 0 | } |
785 | | |
786 | | /* |
787 | | * Locate the proper configuration files and data directory, and read |
788 | | * postgresql.conf for the first time. |
789 | | */ |
790 | 0 | if (!SelectConfigFiles(userDoption, progname)) |
791 | 0 | ExitPostmaster(2); |
792 | |
|
793 | 0 | if (output_config_variable != NULL) |
794 | 0 | { |
795 | | /* |
796 | | * If this is a runtime-computed GUC, it hasn't yet been initialized, |
797 | | * and the present value is not useful. However, this is a convenient |
798 | | * place to print the value for most GUCs because it is safe to run |
799 | | * postmaster startup to this point even if the server is already |
800 | | * running. For the handful of runtime-computed GUCs that we cannot |
801 | | * provide meaningful values for yet, we wait until later in |
802 | | * postmaster startup to print the value. We won't be able to use -C |
803 | | * on running servers for those GUCs, but using this option now would |
804 | | * lead to incorrect results for them. |
805 | | */ |
806 | 0 | int flags = GetConfigOptionFlags(output_config_variable, true); |
807 | |
|
808 | 0 | if ((flags & GUC_RUNTIME_COMPUTED) == 0) |
809 | 0 | { |
810 | | /* |
811 | | * "-C guc" was specified, so print GUC's value and exit. No |
812 | | * extra permission check is needed because the user is reading |
813 | | * inside the data dir. |
814 | | */ |
815 | 0 | const char *config_val = GetConfigOption(output_config_variable, |
816 | 0 | false, false); |
817 | |
|
818 | 0 | puts(config_val ? config_val : ""); |
819 | 0 | ExitPostmaster(0); |
820 | 0 | } |
821 | | |
822 | | /* |
823 | | * A runtime-computed GUC will be printed later on. As we initialize |
824 | | * a server startup sequence, silence any log messages that may show |
825 | | * up in the output generated. FATAL and more severe messages are |
826 | | * useful to show, even if one would only expect at least PANIC. LOG |
827 | | * entries are hidden. |
828 | | */ |
829 | 0 | SetConfigOption("log_min_messages", "FATAL", PGC_SUSET, |
830 | 0 | PGC_S_OVERRIDE); |
831 | 0 | } |
832 | | |
833 | | /* Verify that DataDir looks reasonable */ |
834 | 0 | checkDataDir(); |
835 | | |
836 | | /* Check that pg_control exists */ |
837 | 0 | checkControlFile(); |
838 | | |
839 | | /* And switch working directory into it */ |
840 | 0 | ChangeToDataDir(); |
841 | | |
842 | | /* |
843 | | * Check for invalid combinations of GUC settings. |
844 | | */ |
845 | 0 | if (SuperuserReservedConnections + ReservedConnections >= MaxConnections) |
846 | 0 | { |
847 | 0 | write_stderr("%s: \"superuser_reserved_connections\" (%d) plus \"reserved_connections\" (%d) must be less than \"max_connections\" (%d)\n", |
848 | 0 | progname, |
849 | 0 | SuperuserReservedConnections, ReservedConnections, |
850 | 0 | MaxConnections); |
851 | 0 | ExitPostmaster(1); |
852 | 0 | } |
853 | 0 | if (XLogArchiveMode > ARCHIVE_MODE_OFF && wal_level == WAL_LEVEL_MINIMAL) |
854 | 0 | ereport(ERROR, |
855 | 0 | (errmsg("WAL archival cannot be enabled when \"wal_level\" is \"minimal\""))); |
856 | 0 | if (max_wal_senders > 0 && wal_level == WAL_LEVEL_MINIMAL) |
857 | 0 | ereport(ERROR, |
858 | 0 | (errmsg("WAL streaming (\"max_wal_senders\" > 0) requires \"wal_level\" to be \"replica\" or \"logical\""))); |
859 | 0 | if (summarize_wal && wal_level == WAL_LEVEL_MINIMAL) |
860 | 0 | ereport(ERROR, |
861 | 0 | (errmsg("WAL cannot be summarized when \"wal_level\" is \"minimal\""))); |
862 | 0 | if (sync_replication_slots && wal_level == WAL_LEVEL_MINIMAL) |
863 | 0 | ereport(ERROR, |
864 | 0 | (errmsg("replication slot synchronization (\"sync_replication_slots\" = on) requires \"wal_level\" to be \"replica\" or \"logical\""))); |
865 | | |
866 | | /* |
867 | | * Other one-time internal sanity checks can go here, if they are fast. |
868 | | * (Put any slow processing further down, after postmaster.pid creation.) |
869 | | */ |
870 | 0 | if (!CheckDateTokenTables()) |
871 | 0 | { |
872 | 0 | write_stderr("%s: invalid datetoken tables, please fix\n", progname); |
873 | 0 | ExitPostmaster(1); |
874 | 0 | } |
875 | | |
876 | | /* For debugging: display postmaster environment */ |
877 | 0 | if (message_level_is_interesting(DEBUG3)) |
878 | 0 | { |
879 | 0 | #if !defined(WIN32) |
880 | 0 | extern char **environ; |
881 | 0 | #endif |
882 | 0 | char **p; |
883 | 0 | StringInfoData si; |
884 | |
|
885 | 0 | initStringInfo(&si); |
886 | |
|
887 | 0 | appendStringInfoString(&si, "initial environment dump:"); |
888 | 0 | for (p = environ; *p; ++p) |
889 | 0 | appendStringInfo(&si, "\n%s", *p); |
890 | |
|
891 | 0 | ereport(DEBUG3, errmsg_internal("%s", si.data)); |
892 | 0 | pfree(si.data); |
893 | 0 | } |
894 | | |
895 | | /* |
896 | | * Create lockfile for data directory. |
897 | | * |
898 | | * We want to do this before we try to grab the input sockets, because the |
899 | | * data directory interlock is more reliable than the socket-file |
900 | | * interlock (thanks to whoever decided to put socket files in /tmp :-(). |
901 | | * For the same reason, it's best to grab the TCP socket(s) before the |
902 | | * Unix socket(s). |
903 | | * |
904 | | * Also note that this internally sets up the on_proc_exit function that |
905 | | * is responsible for removing both data directory and socket lockfiles; |
906 | | * so it must happen before opening sockets so that at exit, the socket |
907 | | * lockfiles go away after CloseServerPorts runs. |
908 | | */ |
909 | 0 | CreateDataDirLockFile(true); |
910 | | |
911 | | /* |
912 | | * Read the control file (for error checking and config info). |
913 | | * |
914 | | * Since we verify the control file's CRC, this has a useful side effect |
915 | | * on machines where we need a run-time test for CRC support instructions. |
916 | | * The postmaster will do the test once at startup, and then its child |
917 | | * processes will inherit the correct function pointer and not need to |
918 | | * repeat the test. |
919 | | */ |
920 | 0 | LocalProcessControlFile(false); |
921 | | |
922 | | /* |
923 | | * Register the apply launcher. It's probably a good idea to call this |
924 | | * before any modules had a chance to take the background worker slots. |
925 | | */ |
926 | 0 | ApplyLauncherRegister(); |
927 | | |
928 | | /* |
929 | | * Register the shared memory needs of all core subsystems. |
930 | | */ |
931 | 0 | RegisterBuiltinShmemCallbacks(); |
932 | | |
933 | | /* |
934 | | * process any libraries that should be preloaded at postmaster start |
935 | | */ |
936 | 0 | process_shared_preload_libraries(); |
937 | | |
938 | | /* |
939 | | * Initialize SSL library, if specified. |
940 | | */ |
941 | | #ifdef USE_SSL |
942 | | if (EnableSSL) |
943 | | { |
944 | | (void) secure_initialize(true); |
945 | | LoadedSSL = true; |
946 | | } |
947 | | #endif |
948 | | |
949 | | /* |
950 | | * Now that loadable modules have had their chance to alter any GUCs, |
951 | | * calculate MaxBackends and initialize the machinery to track child |
952 | | * processes. |
953 | | */ |
954 | 0 | InitializeMaxBackends(); |
955 | 0 | InitPostmasterChildSlots(); |
956 | | |
957 | | /* |
958 | | * Calculate the size of the PGPROC fast-path lock arrays. |
959 | | */ |
960 | 0 | InitializeFastPathLocks(); |
961 | | |
962 | | /* |
963 | | * Also call any legacy shmem request hooks that might've been installed |
964 | | * by preloaded libraries. |
965 | | * |
966 | | * Note: this must be done before ShmemCallRequestCallbacks(), because the |
967 | | * hooks may request LWLocks with RequestNamedLWLockTranche(), which in |
968 | | * turn affects the size of the LWLock array calculated in lwlock.c. |
969 | | */ |
970 | 0 | process_shmem_requests(); |
971 | | |
972 | | /* |
973 | | * Ask all subsystems, including preloaded libraries, to register their |
974 | | * shared memory needs. |
975 | | */ |
976 | 0 | ShmemCallRequestCallbacks(); |
977 | | |
978 | | /* |
979 | | * Now that loadable modules have had their chance to request additional |
980 | | * shared memory, determine the value of any runtime-computed GUCs that |
981 | | * depend on the amount of shared memory required. |
982 | | */ |
983 | 0 | InitializeShmemGUCs(); |
984 | | |
985 | | /* |
986 | | * Now that modules have been loaded, we can process any custom resource |
987 | | * managers specified in the wal_consistency_checking GUC. |
988 | | */ |
989 | 0 | InitializeWalConsistencyChecking(); |
990 | | |
991 | | /* |
992 | | * If -C was specified with a runtime-computed GUC, we held off printing |
993 | | * the value earlier, as the GUC was not yet initialized. We handle -C |
994 | | * for most GUCs before we lock the data directory so that the option may |
995 | | * be used on a running server. However, a handful of GUCs are runtime- |
996 | | * computed and do not have meaningful values until after locking the data |
997 | | * directory, and we cannot safely calculate their values earlier on a |
998 | | * running server. At this point, such GUCs should be properly |
999 | | * initialized, and we haven't yet set up shared memory, so this is a good |
1000 | | * time to handle the -C option for these special GUCs. |
1001 | | */ |
1002 | 0 | if (output_config_variable != NULL) |
1003 | 0 | { |
1004 | 0 | const char *config_val = GetConfigOption(output_config_variable, |
1005 | 0 | false, false); |
1006 | |
|
1007 | 0 | puts(config_val ? config_val : ""); |
1008 | 0 | ExitPostmaster(0); |
1009 | 0 | } |
1010 | | |
1011 | | /* |
1012 | | * Set up shared memory and semaphores. |
1013 | | * |
1014 | | * Note: if using SysV shmem and/or semas, each postmaster startup will |
1015 | | * normally choose the same IPC keys. This helps ensure that we will |
1016 | | * clean up dead IPC objects if the postmaster crashes and is restarted. |
1017 | | */ |
1018 | 0 | CreateSharedMemoryAndSemaphores(); |
1019 | | |
1020 | | /* |
1021 | | * Estimate number of openable files. This must happen after setting up |
1022 | | * semaphores, because on some platforms semaphores count as open files. |
1023 | | */ |
1024 | 0 | set_max_safe_fds(); |
1025 | | |
1026 | | /* |
1027 | | * Initialize pipe (or process handle on Windows) that allows children to |
1028 | | * wake up from sleep on postmaster death. |
1029 | | */ |
1030 | 0 | InitPostmasterDeathWatchHandle(); |
1031 | |
|
1032 | | #ifdef WIN32 |
1033 | | |
1034 | | /* |
1035 | | * Initialize I/O completion port used to deliver list of dead children. |
1036 | | */ |
1037 | | win32ChildQueue = CreateIoCompletionPort(INVALID_HANDLE_VALUE, NULL, 0, 1); |
1038 | | if (win32ChildQueue == NULL) |
1039 | | ereport(FATAL, |
1040 | | (errmsg("could not create I/O completion port for child queue"))); |
1041 | | #endif |
1042 | |
|
1043 | | #ifdef EXEC_BACKEND |
1044 | | /* Write out nondefault GUC settings for child processes to use */ |
1045 | | write_nondefault_variables(PGC_POSTMASTER); |
1046 | | |
1047 | | /* |
1048 | | * Clean out the temp directory used to transmit parameters to child |
1049 | | * processes (see internal_forkexec). We must do this before launching |
1050 | | * any child processes, else we have a race condition: we could remove a |
1051 | | * parameter file before the child can read it. It should be safe to do |
1052 | | * so now, because we verified earlier that there are no conflicting |
1053 | | * Postgres processes in this data directory. |
1054 | | */ |
1055 | | RemovePgTempFilesInDir(PG_TEMP_FILES_DIR, true, false); |
1056 | | #endif |
1057 | | |
1058 | | /* |
1059 | | * Forcibly remove the files signaling a standby promotion request. |
1060 | | * Otherwise, the existence of those files triggers a promotion too early, |
1061 | | * whether a user wants that or not. |
1062 | | * |
1063 | | * This removal of files is usually unnecessary because they can exist |
1064 | | * only during a few moments during a standby promotion. However there is |
1065 | | * a race condition: if pg_ctl promote is executed and creates the files |
1066 | | * during a promotion, the files can stay around even after the server is |
1067 | | * brought up to be the primary. Then, if a new standby starts by using |
1068 | | * the backup taken from the new primary, the files can exist at server |
1069 | | * startup and must be removed in order to avoid an unexpected promotion. |
1070 | | * |
1071 | | * Note that promotion signal files need to be removed before the startup |
1072 | | * process is invoked. Because, after that, they can be used by |
1073 | | * postmaster's SIGUSR1 signal handler. |
1074 | | */ |
1075 | 0 | RemovePromoteSignalFiles(); |
1076 | | |
1077 | | /* Do the same for logrotate signal file */ |
1078 | 0 | RemoveLogrotateSignalFiles(); |
1079 | | |
1080 | | /* Remove any outdated file holding the current log filenames. */ |
1081 | 0 | if (unlink(LOG_METAINFO_DATAFILE) < 0 && errno != ENOENT) |
1082 | 0 | ereport(LOG, |
1083 | 0 | (errcode_for_file_access(), |
1084 | 0 | errmsg("could not remove file \"%s\": %m", |
1085 | 0 | LOG_METAINFO_DATAFILE))); |
1086 | | |
1087 | | /* |
1088 | | * If enabled, start up syslogger collection subprocess |
1089 | | */ |
1090 | 0 | if (Logging_collector) |
1091 | 0 | StartSysLogger(); |
1092 | | |
1093 | | /* |
1094 | | * Reset whereToSendOutput from DestDebug (its starting state) to |
1095 | | * DestNone. This stops ereport from sending log messages to stderr unless |
1096 | | * Log_destination permits. We don't do this until the postmaster is |
1097 | | * fully launched, since startup failures may as well be reported to |
1098 | | * stderr. |
1099 | | * |
1100 | | * If we are in fact disabling logging to stderr, first emit a log message |
1101 | | * saying so, to provide a breadcrumb trail for users who may not remember |
1102 | | * that their logging is configured to go somewhere else. |
1103 | | */ |
1104 | 0 | if (!(Log_destination & LOG_DESTINATION_STDERR)) |
1105 | 0 | ereport(LOG, |
1106 | 0 | (errmsg("ending log output to stderr"), |
1107 | 0 | errhint("Future log output will go to log destination \"%s\".", |
1108 | 0 | Log_destination_string))); |
1109 | | |
1110 | 0 | whereToSendOutput = DestNone; |
1111 | | |
1112 | | /* |
1113 | | * Report server startup in log. While we could emit this much earlier, |
1114 | | * it seems best to do so after starting the log collector, if we intend |
1115 | | * to use one. |
1116 | | */ |
1117 | 0 | ereport(LOG, |
1118 | 0 | (errmsg("starting %s", PG_VERSION_STR))); |
1119 | | |
1120 | | /* |
1121 | | * Establish input sockets. |
1122 | | * |
1123 | | * First set up an on_proc_exit function that's charged with closing the |
1124 | | * sockets again at postmaster shutdown. |
1125 | | */ |
1126 | 0 | ListenSockets = palloc(MAXLISTEN * sizeof(pgsocket)); |
1127 | 0 | on_proc_exit(CloseServerPorts, 0); |
1128 | |
|
1129 | 0 | if (ListenAddresses) |
1130 | 0 | { |
1131 | 0 | char *rawstring; |
1132 | 0 | List *elemlist; |
1133 | 0 | ListCell *l; |
1134 | 0 | int success = 0; |
1135 | | |
1136 | | /* Need a modifiable copy of ListenAddresses */ |
1137 | 0 | rawstring = pstrdup(ListenAddresses); |
1138 | | |
1139 | | /* Parse string into list of hostnames */ |
1140 | 0 | if (!SplitGUCList(rawstring, ',', &elemlist)) |
1141 | 0 | { |
1142 | | /* syntax error in list */ |
1143 | 0 | ereport(FATAL, |
1144 | 0 | (errcode(ERRCODE_INVALID_PARAMETER_VALUE), |
1145 | 0 | errmsg("invalid list syntax in parameter \"%s\"", |
1146 | 0 | "listen_addresses"))); |
1147 | 0 | } |
1148 | | |
1149 | 0 | foreach(l, elemlist) |
1150 | 0 | { |
1151 | 0 | char *curhost = (char *) lfirst(l); |
1152 | |
|
1153 | 0 | if (strcmp(curhost, "*") == 0) |
1154 | 0 | status = ListenServerPort(AF_UNSPEC, NULL, |
1155 | 0 | (unsigned short) PostPortNumber, |
1156 | 0 | NULL, |
1157 | 0 | ListenSockets, |
1158 | 0 | &NumListenSockets, |
1159 | 0 | MAXLISTEN); |
1160 | 0 | else |
1161 | 0 | status = ListenServerPort(AF_UNSPEC, curhost, |
1162 | 0 | (unsigned short) PostPortNumber, |
1163 | 0 | NULL, |
1164 | 0 | ListenSockets, |
1165 | 0 | &NumListenSockets, |
1166 | 0 | MAXLISTEN); |
1167 | |
|
1168 | 0 | if (status == STATUS_OK) |
1169 | 0 | { |
1170 | 0 | success++; |
1171 | | /* record the first successful host addr in lockfile */ |
1172 | 0 | if (!listen_addr_saved) |
1173 | 0 | { |
1174 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_LISTEN_ADDR, curhost); |
1175 | 0 | listen_addr_saved = true; |
1176 | 0 | } |
1177 | 0 | } |
1178 | 0 | else |
1179 | 0 | ereport(WARNING, |
1180 | 0 | (errmsg("could not create listen socket for \"%s\"", |
1181 | 0 | curhost))); |
1182 | 0 | } |
1183 | | |
1184 | 0 | if (!success && elemlist != NIL) |
1185 | 0 | ereport(FATAL, |
1186 | 0 | (errmsg("could not create any TCP/IP sockets"))); |
1187 | | |
1188 | 0 | list_free(elemlist); |
1189 | 0 | pfree(rawstring); |
1190 | 0 | } |
1191 | | |
1192 | | #ifdef USE_BONJOUR |
1193 | | /* Register for Bonjour only if we opened TCP socket(s) */ |
1194 | | if (enable_bonjour && NumListenSockets > 0) |
1195 | | { |
1196 | | DNSServiceErrorType err; |
1197 | | |
1198 | | /* |
1199 | | * We pass 0 for interface_index, which will result in registering on |
1200 | | * all "applicable" interfaces. It's not entirely clear from the |
1201 | | * DNS-SD docs whether this would be appropriate if we have bound to |
1202 | | * just a subset of the available network interfaces. |
1203 | | */ |
1204 | | err = DNSServiceRegister(&bonjour_sdref, |
1205 | | 0, |
1206 | | 0, |
1207 | | bonjour_name, |
1208 | | "_postgresql._tcp.", |
1209 | | NULL, |
1210 | | NULL, |
1211 | | pg_hton16(PostPortNumber), |
1212 | | 0, |
1213 | | NULL, |
1214 | | NULL, |
1215 | | NULL); |
1216 | | if (err != kDNSServiceErr_NoError) |
1217 | | ereport(LOG, |
1218 | | (errmsg("DNSServiceRegister() failed: error code %ld", |
1219 | | (long) err))); |
1220 | | |
1221 | | /* |
1222 | | * We don't bother to read the mDNS daemon's reply, and we expect that |
1223 | | * it will automatically terminate our registration when the socket is |
1224 | | * closed at postmaster termination. So there's nothing more to be |
1225 | | * done here. However, the bonjour_sdref is kept around so that |
1226 | | * forked children can close their copies of the socket. |
1227 | | */ |
1228 | | } |
1229 | | #endif |
1230 | | |
1231 | 0 | if (Unix_socket_directories) |
1232 | 0 | { |
1233 | 0 | char *rawstring; |
1234 | 0 | List *elemlist; |
1235 | 0 | ListCell *l; |
1236 | 0 | int success = 0; |
1237 | | |
1238 | | /* Need a modifiable copy of Unix_socket_directories */ |
1239 | 0 | rawstring = pstrdup(Unix_socket_directories); |
1240 | | |
1241 | | /* Parse string into list of directories */ |
1242 | 0 | if (!SplitDirectoriesString(rawstring, ',', &elemlist)) |
1243 | 0 | { |
1244 | | /* syntax error in list */ |
1245 | 0 | ereport(FATAL, |
1246 | 0 | (errcode(ERRCODE_INVALID_PARAMETER_VALUE), |
1247 | 0 | errmsg("invalid list syntax in parameter \"%s\"", |
1248 | 0 | "unix_socket_directories"))); |
1249 | 0 | } |
1250 | | |
1251 | 0 | foreach(l, elemlist) |
1252 | 0 | { |
1253 | 0 | char *socketdir = (char *) lfirst(l); |
1254 | |
|
1255 | 0 | status = ListenServerPort(AF_UNIX, NULL, |
1256 | 0 | (unsigned short) PostPortNumber, |
1257 | 0 | socketdir, |
1258 | 0 | ListenSockets, |
1259 | 0 | &NumListenSockets, |
1260 | 0 | MAXLISTEN); |
1261 | |
|
1262 | 0 | if (status == STATUS_OK) |
1263 | 0 | { |
1264 | 0 | success++; |
1265 | | /* record the first successful Unix socket in lockfile */ |
1266 | 0 | if (success == 1) |
1267 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_SOCKET_DIR, socketdir); |
1268 | 0 | } |
1269 | 0 | else |
1270 | 0 | ereport(WARNING, |
1271 | 0 | (errmsg("could not create Unix-domain socket in directory \"%s\"", |
1272 | 0 | socketdir))); |
1273 | 0 | } |
1274 | | |
1275 | 0 | if (!success && elemlist != NIL) |
1276 | 0 | ereport(FATAL, |
1277 | 0 | (errmsg("could not create any Unix-domain sockets"))); |
1278 | | |
1279 | 0 | list_free_deep(elemlist); |
1280 | 0 | pfree(rawstring); |
1281 | 0 | } |
1282 | | |
1283 | | /* |
1284 | | * check that we have some socket to listen on |
1285 | | */ |
1286 | 0 | if (NumListenSockets == 0) |
1287 | 0 | ereport(FATAL, |
1288 | 0 | (errmsg("no socket created for listening"))); |
1289 | | |
1290 | | /* |
1291 | | * If no valid TCP ports, write an empty line for listen address, |
1292 | | * indicating the Unix socket must be used. Note that this line is not |
1293 | | * added to the lock file until there is a socket backing it. |
1294 | | */ |
1295 | 0 | if (!listen_addr_saved) |
1296 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_LISTEN_ADDR, ""); |
1297 | | |
1298 | | /* |
1299 | | * Record postmaster options. We delay this till now to avoid recording |
1300 | | * bogus options (eg, unusable port number). |
1301 | | */ |
1302 | 0 | if (!CreateOptsFile(argc, argv, my_exec_path)) |
1303 | 0 | ExitPostmaster(1); |
1304 | | |
1305 | | /* |
1306 | | * Write the external PID file if requested |
1307 | | */ |
1308 | 0 | if (external_pid_file) |
1309 | 0 | { |
1310 | 0 | FILE *fpidfile = fopen(external_pid_file, "w"); |
1311 | |
|
1312 | 0 | if (fpidfile) |
1313 | 0 | { |
1314 | 0 | fprintf(fpidfile, "%d\n", MyProcPid); |
1315 | 0 | fclose(fpidfile); |
1316 | | |
1317 | | /* Make PID file world readable */ |
1318 | 0 | if (chmod(external_pid_file, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH) != 0) |
1319 | 0 | write_stderr("%s: could not change permissions of external PID file \"%s\": %m\n", |
1320 | 0 | progname, external_pid_file); |
1321 | 0 | } |
1322 | 0 | else |
1323 | 0 | write_stderr("%s: could not write external PID file \"%s\": %m\n", |
1324 | 0 | progname, external_pid_file); |
1325 | |
|
1326 | 0 | on_proc_exit(unlink_external_pid_file, 0); |
1327 | 0 | } |
1328 | | |
1329 | | /* |
1330 | | * Remove old temporary files. At this point there can be no other |
1331 | | * Postgres processes running in this directory, so this should be safe. |
1332 | | */ |
1333 | 0 | RemovePgTempFiles(); |
1334 | | |
1335 | | /* |
1336 | | * Initialize the autovacuum subsystem (again, no process start yet) |
1337 | | */ |
1338 | 0 | autovac_init(); |
1339 | | |
1340 | | /* |
1341 | | * Load configuration files for client authentication. |
1342 | | */ |
1343 | 0 | if (!load_hba()) |
1344 | 0 | { |
1345 | | /* |
1346 | | * It makes no sense to continue if we fail to load the HBA file, |
1347 | | * since there is no way to connect to the database in this case. |
1348 | | */ |
1349 | 0 | ereport(FATAL, |
1350 | | /* translator: %s is a configuration file */ |
1351 | 0 | (errmsg("could not load %s", HbaFileName))); |
1352 | 0 | } |
1353 | 0 | if (!load_ident()) |
1354 | 0 | { |
1355 | | /* |
1356 | | * We can start up without the IDENT file, although it means that you |
1357 | | * cannot log in using any of the authentication methods that need a |
1358 | | * user name mapping. load_ident() already logged the details of error |
1359 | | * to the log. |
1360 | | */ |
1361 | 0 | } |
1362 | |
|
1363 | | #ifdef HAVE_PTHREAD_IS_THREADED_NP |
1364 | | |
1365 | | /* |
1366 | | * On macOS, libintl replaces setlocale() with a version that calls |
1367 | | * CFLocaleCopyCurrent() when its second argument is "" and every relevant |
1368 | | * environment variable is unset or empty. CFLocaleCopyCurrent() makes |
1369 | | * the process multithreaded. The postmaster calls sigprocmask() and |
1370 | | * calls fork() without an immediate exec(), both of which have undefined |
1371 | | * behavior in a multithreaded program. A multithreaded postmaster is the |
1372 | | * normal case on Windows, which offers neither fork() nor sigprocmask(). |
1373 | | * Currently, macOS is the only platform having pthread_is_threaded_np(), |
1374 | | * so we need not worry whether this HINT is appropriate elsewhere. |
1375 | | */ |
1376 | | if (pthread_is_threaded_np() != 0) |
1377 | | ereport(FATAL, |
1378 | | (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), |
1379 | | errmsg("postmaster became multithreaded during startup"), |
1380 | | errhint("Set the LC_ALL environment variable to a valid locale."))); |
1381 | | #endif |
1382 | | |
1383 | | /* |
1384 | | * Remember postmaster startup time |
1385 | | */ |
1386 | 0 | PgStartTime = GetCurrentTimestamp(); |
1387 | | |
1388 | | /* |
1389 | | * Report postmaster status in the postmaster.pid file, to allow pg_ctl to |
1390 | | * see what's happening. |
1391 | | */ |
1392 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STARTING); |
1393 | |
|
1394 | 0 | UpdatePMState(PM_STARTUP); |
1395 | | |
1396 | | /* Make sure we can perform I/O while starting up. */ |
1397 | 0 | maybe_start_io_workers(); |
1398 | | |
1399 | | /* Start bgwriter and checkpointer so they can help with recovery */ |
1400 | 0 | if (CheckpointerPMChild == NULL) |
1401 | 0 | CheckpointerPMChild = StartChildProcess(B_CHECKPOINTER); |
1402 | 0 | if (BgWriterPMChild == NULL) |
1403 | 0 | BgWriterPMChild = StartChildProcess(B_BG_WRITER); |
1404 | | |
1405 | | /* |
1406 | | * We're ready to rock and roll... |
1407 | | */ |
1408 | 0 | StartupPMChild = StartChildProcess(B_STARTUP); |
1409 | 0 | Assert(StartupPMChild != NULL); |
1410 | 0 | StartupStatus = STARTUP_RUNNING; |
1411 | | |
1412 | | /* Some workers may be scheduled to start now */ |
1413 | 0 | maybe_start_bgworkers(); |
1414 | |
|
1415 | 0 | status = ServerLoop(); |
1416 | | |
1417 | | /* |
1418 | | * ServerLoop probably shouldn't ever return, but if it does, close down. |
1419 | | */ |
1420 | 0 | ExitPostmaster(status != STATUS_OK); |
1421 | |
|
1422 | 0 | abort(); /* not reached */ |
1423 | 0 | } |
1424 | | |
1425 | | |
1426 | | /* |
1427 | | * on_proc_exit callback to close server's listen sockets |
1428 | | */ |
1429 | | static void |
1430 | | CloseServerPorts(int status, Datum arg) |
1431 | | { |
1432 | | int i; |
1433 | | |
1434 | | /* |
1435 | | * First, explicitly close all the socket FDs. We used to just let this |
1436 | | * happen implicitly at postmaster exit, but it's better to close them |
1437 | | * before we remove the postmaster.pid lockfile; otherwise there's a race |
1438 | | * condition if a new postmaster wants to re-use the TCP port number. |
1439 | | */ |
1440 | | for (i = 0; i < NumListenSockets; i++) |
1441 | | { |
1442 | | if (closesocket(ListenSockets[i]) != 0) |
1443 | | elog(LOG, "could not close listen socket: %m"); |
1444 | | } |
1445 | | NumListenSockets = 0; |
1446 | | |
1447 | | /* |
1448 | | * Next, remove any filesystem entries for Unix sockets. To avoid race |
1449 | | * conditions against incoming postmasters, this must happen after closing |
1450 | | * the sockets and before removing lock files. |
1451 | | */ |
1452 | | RemoveSocketFiles(); |
1453 | | |
1454 | | /* |
1455 | | * We don't do anything about socket lock files here; those will be |
1456 | | * removed in a later on_proc_exit callback. |
1457 | | */ |
1458 | | } |
1459 | | |
1460 | | /* |
1461 | | * on_proc_exit callback to delete external_pid_file |
1462 | | */ |
1463 | | static void |
1464 | | unlink_external_pid_file(int status, Datum arg) |
1465 | 0 | { |
1466 | 0 | if (external_pid_file) |
1467 | 0 | unlink(external_pid_file); |
1468 | 0 | } |
1469 | | |
1470 | | |
1471 | | /* |
1472 | | * Compute and check the directory paths to files that are part of the |
1473 | | * installation (as deduced from the postgres executable's own location) |
1474 | | */ |
1475 | | static void |
1476 | | getInstallationPaths(const char *argv0) |
1477 | 0 | { |
1478 | 0 | DIR *pdir; |
1479 | | |
1480 | | /* Locate the postgres executable itself */ |
1481 | 0 | if (find_my_exec(argv0, my_exec_path) < 0) |
1482 | 0 | ereport(FATAL, |
1483 | 0 | (errmsg("%s: could not locate my own executable path", argv0))); |
1484 | | |
1485 | | #ifdef EXEC_BACKEND |
1486 | | /* Locate executable backend before we change working directory */ |
1487 | | if (find_other_exec(argv0, "postgres", PG_BACKEND_VERSIONSTR, |
1488 | | postgres_exec_path) < 0) |
1489 | | ereport(FATAL, |
1490 | | (errmsg("%s: could not locate matching postgres executable", |
1491 | | argv0))); |
1492 | | #endif |
1493 | | |
1494 | | /* |
1495 | | * Locate the pkglib directory --- this has to be set early in case we try |
1496 | | * to load any modules from it in response to postgresql.conf entries. |
1497 | | */ |
1498 | 0 | get_pkglib_path(my_exec_path, pkglib_path); |
1499 | | |
1500 | | /* |
1501 | | * Verify that there's a readable directory there; otherwise the Postgres |
1502 | | * installation is incomplete or corrupt. (A typical cause of this |
1503 | | * failure is that the postgres executable has been moved or hardlinked to |
1504 | | * some directory that's not a sibling of the installation lib/ |
1505 | | * directory.) |
1506 | | */ |
1507 | 0 | pdir = AllocateDir(pkglib_path); |
1508 | 0 | if (pdir == NULL) |
1509 | 0 | ereport(ERROR, |
1510 | 0 | (errcode_for_file_access(), |
1511 | 0 | errmsg("could not open directory \"%s\": %m", |
1512 | 0 | pkglib_path), |
1513 | 0 | errhint("This may indicate an incomplete PostgreSQL installation, or that the file \"%s\" has been moved away from its proper location.", |
1514 | 0 | my_exec_path))); |
1515 | 0 | FreeDir(pdir); |
1516 | | |
1517 | | /* |
1518 | | * It's not worth checking the share/ directory. If the lib/ directory is |
1519 | | * there, then share/ probably is too. |
1520 | | */ |
1521 | 0 | } |
1522 | | |
1523 | | /* |
1524 | | * Check that pg_control exists in the correct location in the data directory. |
1525 | | * |
1526 | | * No attempt is made to validate the contents of pg_control here. This is |
1527 | | * just a sanity check to see if we are looking at a real data directory. |
1528 | | */ |
1529 | | static void |
1530 | | checkControlFile(void) |
1531 | 0 | { |
1532 | 0 | char path[MAXPGPATH]; |
1533 | 0 | FILE *fp; |
1534 | |
|
1535 | 0 | snprintf(path, sizeof(path), "%s/%s", DataDir, XLOG_CONTROL_FILE); |
1536 | |
|
1537 | 0 | fp = AllocateFile(path, PG_BINARY_R); |
1538 | 0 | if (fp == NULL) |
1539 | 0 | { |
1540 | 0 | write_stderr("%s: could not find the database system\n" |
1541 | 0 | "Expected to find it in the directory \"%s\",\n" |
1542 | 0 | "but could not open file \"%s\": %m\n", |
1543 | 0 | progname, DataDir, path); |
1544 | 0 | ExitPostmaster(2); |
1545 | 0 | } |
1546 | 0 | FreeFile(fp); |
1547 | 0 | } |
1548 | | |
1549 | | /* |
1550 | | * Determine how long should we let ServerLoop sleep, in milliseconds. |
1551 | | * |
1552 | | * In normal conditions we wait at most one minute, to ensure that the other |
1553 | | * background tasks handled by ServerLoop get done even when no requests are |
1554 | | * arriving. However, if there are background workers waiting to be started, |
1555 | | * we don't actually sleep so that they are quickly serviced. Other exception |
1556 | | * cases are as shown in the code. |
1557 | | */ |
1558 | | static int |
1559 | | DetermineSleepTime(void) |
1560 | 0 | { |
1561 | 0 | TimestampTz next_wakeup; |
1562 | | |
1563 | | /* |
1564 | | * If in ImmediateShutdown with a SIGKILL timeout, ignore everything else |
1565 | | * and wait for that. |
1566 | | * |
1567 | | * XXX Shouldn't this also test FatalError? |
1568 | | */ |
1569 | 0 | if (Shutdown >= ImmediateShutdown) |
1570 | 0 | { |
1571 | 0 | if (AbortStartTime != 0) |
1572 | 0 | { |
1573 | 0 | time_t curtime = time(NULL); |
1574 | 0 | int seconds; |
1575 | | |
1576 | | /* |
1577 | | * time left to abort; clamp to 0 if it already expired, or if |
1578 | | * time goes backwards |
1579 | | */ |
1580 | 0 | if (curtime < AbortStartTime || |
1581 | 0 | curtime - AbortStartTime >= SIGKILL_CHILDREN_AFTER_SECS) |
1582 | 0 | seconds = 0; |
1583 | 0 | else |
1584 | 0 | seconds = SIGKILL_CHILDREN_AFTER_SECS - |
1585 | 0 | (curtime - AbortStartTime); |
1586 | |
|
1587 | 0 | return seconds * 1000; |
1588 | 0 | } |
1589 | 0 | } |
1590 | | |
1591 | | /* Time of next maybe_start_io_workers() call, or 0 for none. */ |
1592 | 0 | next_wakeup = maybe_start_io_workers_scheduled_at(); |
1593 | | |
1594 | | /* Ignore bgworkers during shutdown. */ |
1595 | 0 | if (StartWorkerNeeded && Shutdown == NoShutdown) |
1596 | 0 | return 0; |
1597 | | |
1598 | 0 | if (HaveCrashedWorker && Shutdown == NoShutdown) |
1599 | 0 | { |
1600 | 0 | dlist_mutable_iter iter; |
1601 | | |
1602 | | /* |
1603 | | * When there are crashed bgworkers, we sleep just long enough that |
1604 | | * they are restarted when they request to be. Scan the list to |
1605 | | * determine the minimum of all wakeup times according to most recent |
1606 | | * crash time and requested restart interval. |
1607 | | */ |
1608 | 0 | dlist_foreach_modify(iter, &BackgroundWorkerList) |
1609 | 0 | { |
1610 | 0 | RegisteredBgWorker *rw; |
1611 | 0 | TimestampTz this_wakeup; |
1612 | |
|
1613 | 0 | rw = dlist_container(RegisteredBgWorker, rw_lnode, iter.cur); |
1614 | |
|
1615 | 0 | if (rw->rw_crashed_at == 0) |
1616 | 0 | continue; |
1617 | | |
1618 | 0 | if (rw->rw_worker.bgw_restart_time == BGW_NEVER_RESTART |
1619 | 0 | || rw->rw_terminate) |
1620 | 0 | { |
1621 | 0 | ForgetBackgroundWorker(rw); |
1622 | 0 | continue; |
1623 | 0 | } |
1624 | | |
1625 | 0 | this_wakeup = TimestampTzPlusMilliseconds(rw->rw_crashed_at, |
1626 | 0 | 1000L * rw->rw_worker.bgw_restart_time); |
1627 | 0 | if (next_wakeup == 0 || this_wakeup < next_wakeup) |
1628 | 0 | next_wakeup = this_wakeup; |
1629 | 0 | } |
1630 | 0 | } |
1631 | |
|
1632 | 0 | if (next_wakeup != 0) |
1633 | 0 | { |
1634 | 0 | int ms; |
1635 | | |
1636 | | /* result of TimestampDifferenceMilliseconds is in [0, INT_MAX] */ |
1637 | 0 | ms = (int) TimestampDifferenceMilliseconds(GetCurrentTimestamp(), |
1638 | 0 | next_wakeup); |
1639 | 0 | return Min(60 * 1000, ms); |
1640 | 0 | } |
1641 | | |
1642 | 0 | return 60 * 1000; |
1643 | 0 | } |
1644 | | |
1645 | | /* |
1646 | | * Activate or deactivate notifications of server socket events. Since we |
1647 | | * don't currently have a way to remove events from an existing WaitEventSet, |
1648 | | * we'll just destroy and recreate the whole thing. This is called during |
1649 | | * shutdown so we can wait for backends to exit without accepting new |
1650 | | * connections, and during crash reinitialization when we need to start |
1651 | | * listening for new connections again. The WaitEventSet will be freed in fork |
1652 | | * children by ClosePostmasterPorts(). |
1653 | | */ |
1654 | | static void |
1655 | | ConfigurePostmasterWaitSet(bool accept_connections) |
1656 | 0 | { |
1657 | 0 | if (pm_wait_set) |
1658 | 0 | FreeWaitEventSet(pm_wait_set); |
1659 | 0 | pm_wait_set = NULL; |
1660 | |
|
1661 | 0 | pm_wait_set = CreateWaitEventSet(NULL, |
1662 | 0 | accept_connections ? (1 + NumListenSockets) : 1); |
1663 | 0 | AddWaitEventToSet(pm_wait_set, WL_LATCH_SET, PGINVALID_SOCKET, MyLatch, |
1664 | 0 | NULL); |
1665 | |
|
1666 | 0 | if (accept_connections) |
1667 | 0 | { |
1668 | 0 | for (int i = 0; i < NumListenSockets; i++) |
1669 | 0 | AddWaitEventToSet(pm_wait_set, WL_SOCKET_ACCEPT, ListenSockets[i], |
1670 | 0 | NULL, NULL); |
1671 | 0 | } |
1672 | 0 | } |
1673 | | |
1674 | | /* |
1675 | | * Main idle loop of postmaster |
1676 | | */ |
1677 | | static int |
1678 | | ServerLoop(void) |
1679 | 0 | { |
1680 | 0 | time_t last_lockfile_recheck_time, |
1681 | 0 | last_touch_time; |
1682 | 0 | WaitEvent events[MAXLISTEN]; |
1683 | 0 | int nevents; |
1684 | |
|
1685 | 0 | ConfigurePostmasterWaitSet(true); |
1686 | 0 | last_lockfile_recheck_time = last_touch_time = time(NULL); |
1687 | |
|
1688 | 0 | for (;;) |
1689 | 0 | { |
1690 | 0 | time_t now; |
1691 | |
|
1692 | 0 | nevents = WaitEventSetWait(pm_wait_set, |
1693 | 0 | DetermineSleepTime(), |
1694 | 0 | events, |
1695 | 0 | lengthof(events), |
1696 | 0 | 0 /* postmaster posts no wait_events */ ); |
1697 | | |
1698 | | /* |
1699 | | * Latch set by signal handler, or new connection pending on any of |
1700 | | * our sockets? If the latter, fork a child process to deal with it. |
1701 | | */ |
1702 | 0 | for (int i = 0; i < nevents; i++) |
1703 | 0 | { |
1704 | 0 | if (events[i].events & WL_LATCH_SET) |
1705 | 0 | ResetLatch(MyLatch); |
1706 | | |
1707 | | /* |
1708 | | * The following requests are handled unconditionally, even if we |
1709 | | * didn't see WL_LATCH_SET. This gives high priority to shutdown |
1710 | | * and reload requests where the latch happens to appear later in |
1711 | | * events[] or will be reported by a later call to |
1712 | | * WaitEventSetWait(). |
1713 | | */ |
1714 | 0 | if (pending_pm_shutdown_request) |
1715 | 0 | process_pm_shutdown_request(); |
1716 | 0 | if (pending_pm_reload_request) |
1717 | 0 | process_pm_reload_request(); |
1718 | 0 | if (pending_pm_child_exit) |
1719 | 0 | process_pm_child_exit(); |
1720 | 0 | if (pending_pm_pmsignal) |
1721 | 0 | process_pm_pmsignal(); |
1722 | |
|
1723 | 0 | if (events[i].events & WL_SOCKET_ACCEPT) |
1724 | 0 | { |
1725 | 0 | ClientSocket s; |
1726 | |
|
1727 | 0 | if (AcceptConnection(events[i].fd, &s) == STATUS_OK) |
1728 | 0 | BackendStartup(&s); |
1729 | | |
1730 | | /* We no longer need the open socket in this process */ |
1731 | 0 | if (s.sock != PGINVALID_SOCKET) |
1732 | 0 | { |
1733 | 0 | if (closesocket(s.sock) != 0) |
1734 | 0 | elog(LOG, "could not close client socket: %m"); |
1735 | 0 | } |
1736 | 0 | } |
1737 | 0 | } |
1738 | | |
1739 | | /* |
1740 | | * If we need to launch any background processes after changing state |
1741 | | * or because some exited, do so now. |
1742 | | */ |
1743 | 0 | LaunchMissingBackgroundProcesses(); |
1744 | | |
1745 | | /* If we need to signal the autovacuum launcher, do so now */ |
1746 | 0 | if (avlauncher_needs_signal) |
1747 | 0 | { |
1748 | 0 | avlauncher_needs_signal = false; |
1749 | 0 | if (AutoVacLauncherPMChild != NULL) |
1750 | 0 | signal_child(AutoVacLauncherPMChild, SIGUSR2); |
1751 | 0 | } |
1752 | |
|
1753 | | #ifdef HAVE_PTHREAD_IS_THREADED_NP |
1754 | | |
1755 | | /* |
1756 | | * With assertions enabled, check regularly for appearance of |
1757 | | * additional threads. All builds check at start and exit. |
1758 | | */ |
1759 | | Assert(pthread_is_threaded_np() == 0); |
1760 | | #endif |
1761 | | |
1762 | | /* |
1763 | | * Lastly, check to see if it's time to do some things that we don't |
1764 | | * want to do every single time through the loop, because they're a |
1765 | | * bit expensive. Note that there's up to a minute of slop in when |
1766 | | * these tasks will be performed, since DetermineSleepTime() will let |
1767 | | * us sleep at most that long; except for SIGKILL timeout which has |
1768 | | * special-case logic there. |
1769 | | */ |
1770 | 0 | now = time(NULL); |
1771 | | |
1772 | | /* |
1773 | | * If we already sent SIGQUIT to children and they are slow to shut |
1774 | | * down, it's time to send them SIGKILL (or SIGABRT if requested). |
1775 | | * This doesn't happen normally, but under certain conditions backends |
1776 | | * can get stuck while shutting down. This is a last measure to get |
1777 | | * them unwedged. |
1778 | | * |
1779 | | * Note we also do this during recovery from a process crash. |
1780 | | */ |
1781 | 0 | if ((Shutdown >= ImmediateShutdown || FatalError) && |
1782 | 0 | AbortStartTime != 0 && |
1783 | 0 | (now - AbortStartTime) >= SIGKILL_CHILDREN_AFTER_SECS) |
1784 | 0 | { |
1785 | | /* We were gentle with them before. Not anymore */ |
1786 | 0 | ereport(LOG, |
1787 | | /* translator: %s is SIGKILL or SIGABRT */ |
1788 | 0 | (errmsg("issuing %s to recalcitrant children", |
1789 | 0 | send_abort_for_kill ? "SIGABRT" : "SIGKILL"))); |
1790 | 0 | TerminateChildren(send_abort_for_kill ? SIGABRT : SIGKILL); |
1791 | | /* reset flag so we don't SIGKILL again */ |
1792 | 0 | AbortStartTime = 0; |
1793 | 0 | } |
1794 | | |
1795 | | /* |
1796 | | * Once a minute, verify that postmaster.pid hasn't been removed or |
1797 | | * overwritten. If it has, we force a shutdown. This avoids having |
1798 | | * postmasters and child processes hanging around after their database |
1799 | | * is gone, and maybe causing problems if a new database cluster is |
1800 | | * created in the same place. It also provides some protection |
1801 | | * against a DBA foolishly removing postmaster.pid and manually |
1802 | | * starting a new postmaster. Data corruption is likely to ensue from |
1803 | | * that anyway, but we can minimize the damage by aborting ASAP. |
1804 | | */ |
1805 | 0 | if (now - last_lockfile_recheck_time >= 1 * SECS_PER_MINUTE) |
1806 | 0 | { |
1807 | 0 | if (!RecheckDataDirLockFile()) |
1808 | 0 | { |
1809 | 0 | ereport(LOG, |
1810 | 0 | (errmsg("performing immediate shutdown because data directory lock file is invalid"))); |
1811 | 0 | kill(MyProcPid, SIGQUIT); |
1812 | 0 | } |
1813 | 0 | last_lockfile_recheck_time = now; |
1814 | 0 | } |
1815 | | |
1816 | | /* |
1817 | | * Touch Unix socket and lock files every 58 minutes, to ensure that |
1818 | | * they are not removed by overzealous /tmp-cleaning tasks. We assume |
1819 | | * no one runs cleaners with cutoff times of less than an hour ... |
1820 | | */ |
1821 | 0 | if (now - last_touch_time >= 58 * SECS_PER_MINUTE) |
1822 | 0 | { |
1823 | 0 | TouchSocketFiles(); |
1824 | 0 | TouchSocketLockFiles(); |
1825 | 0 | last_touch_time = now; |
1826 | 0 | } |
1827 | 0 | } |
1828 | 0 | } |
1829 | | |
1830 | | /* |
1831 | | * canAcceptConnections --- check to see if database state allows connections |
1832 | | * of the specified type. backend_type can be B_BACKEND or B_AUTOVAC_WORKER. |
1833 | | * (Note that we don't yet know whether a normal B_BACKEND connection might |
1834 | | * turn into a walsender.) |
1835 | | */ |
1836 | | static CAC_state |
1837 | | canAcceptConnections(BackendType backend_type) |
1838 | 0 | { |
1839 | 0 | CAC_state result = CAC_OK; |
1840 | |
|
1841 | 0 | Assert(backend_type == B_BACKEND || backend_type == B_AUTOVAC_WORKER); |
1842 | | |
1843 | | /* |
1844 | | * Can't start backends when in startup/shutdown/inconsistent recovery |
1845 | | * state. We treat autovac workers the same as user backends for this |
1846 | | * purpose. |
1847 | | */ |
1848 | 0 | if (pmState != PM_RUN && pmState != PM_HOT_STANDBY) |
1849 | 0 | { |
1850 | 0 | if (Shutdown > NoShutdown) |
1851 | 0 | return CAC_SHUTDOWN; /* shutdown is pending */ |
1852 | 0 | else if (!FatalError && pmState == PM_STARTUP) |
1853 | 0 | return CAC_STARTUP; /* normal startup */ |
1854 | 0 | else if (!FatalError && pmState == PM_RECOVERY) |
1855 | 0 | return CAC_NOTHOTSTANDBY; /* not yet ready for hot standby */ |
1856 | 0 | else |
1857 | 0 | return CAC_RECOVERY; /* else must be crash recovery */ |
1858 | 0 | } |
1859 | | |
1860 | | /* |
1861 | | * "Smart shutdown" restrictions are applied only to normal connections, |
1862 | | * not to autovac workers. |
1863 | | */ |
1864 | 0 | if (!connsAllowed && backend_type == B_BACKEND) |
1865 | 0 | return CAC_SHUTDOWN; /* shutdown is pending */ |
1866 | | |
1867 | 0 | return result; |
1868 | 0 | } |
1869 | | |
1870 | | /* |
1871 | | * ClosePostmasterPorts -- close all the postmaster's open sockets |
1872 | | * |
1873 | | * This is called during child process startup to release file descriptors |
1874 | | * that are not needed by that child process. The postmaster still has |
1875 | | * them open, of course. |
1876 | | * |
1877 | | * Note: we pass am_syslogger as a boolean because we don't want to set |
1878 | | * the global variable yet when this is called. |
1879 | | */ |
1880 | | void |
1881 | | ClosePostmasterPorts(bool am_syslogger) |
1882 | 0 | { |
1883 | | /* Release resources held by the postmaster's WaitEventSet. */ |
1884 | 0 | if (pm_wait_set) |
1885 | 0 | { |
1886 | 0 | FreeWaitEventSetAfterFork(pm_wait_set); |
1887 | 0 | pm_wait_set = NULL; |
1888 | 0 | } |
1889 | |
|
1890 | 0 | #ifndef WIN32 |
1891 | | |
1892 | | /* |
1893 | | * Close the write end of postmaster death watch pipe. It's important to |
1894 | | * do this as early as possible, so that if postmaster dies, others won't |
1895 | | * think that it's still running because we're holding the pipe open. |
1896 | | */ |
1897 | 0 | if (close(postmaster_alive_fds[POSTMASTER_FD_OWN]) != 0) |
1898 | 0 | ereport(FATAL, |
1899 | 0 | (errcode_for_file_access(), |
1900 | 0 | errmsg_internal("could not close postmaster death monitoring pipe in child process: %m"))); |
1901 | 0 | postmaster_alive_fds[POSTMASTER_FD_OWN] = -1; |
1902 | | /* Notify fd.c that we released one pipe FD. */ |
1903 | 0 | ReleaseExternalFD(); |
1904 | 0 | #endif |
1905 | | |
1906 | | /* |
1907 | | * Close the postmaster's listen sockets. These aren't tracked by fd.c, |
1908 | | * so we don't call ReleaseExternalFD() here. |
1909 | | * |
1910 | | * The listen sockets are marked as FD_CLOEXEC, so this isn't needed in |
1911 | | * EXEC_BACKEND mode. |
1912 | | */ |
1913 | 0 | #ifndef EXEC_BACKEND |
1914 | 0 | if (ListenSockets) |
1915 | 0 | { |
1916 | 0 | for (int i = 0; i < NumListenSockets; i++) |
1917 | 0 | { |
1918 | 0 | if (closesocket(ListenSockets[i]) != 0) |
1919 | 0 | elog(LOG, "could not close listen socket: %m"); |
1920 | 0 | } |
1921 | 0 | pfree(ListenSockets); |
1922 | 0 | } |
1923 | 0 | NumListenSockets = 0; |
1924 | 0 | ListenSockets = NULL; |
1925 | 0 | #endif |
1926 | | |
1927 | | /* |
1928 | | * If using syslogger, close the read side of the pipe. We don't bother |
1929 | | * tracking this in fd.c, either. |
1930 | | */ |
1931 | 0 | if (!am_syslogger) |
1932 | 0 | { |
1933 | 0 | #ifndef WIN32 |
1934 | 0 | if (syslogPipe[0] >= 0) |
1935 | 0 | close(syslogPipe[0]); |
1936 | 0 | syslogPipe[0] = -1; |
1937 | | #else |
1938 | | if (syslogPipe[0]) |
1939 | | CloseHandle(syslogPipe[0]); |
1940 | | syslogPipe[0] = 0; |
1941 | | #endif |
1942 | 0 | } |
1943 | |
|
1944 | | #ifdef USE_BONJOUR |
1945 | | /* If using Bonjour, close the connection to the mDNS daemon */ |
1946 | | if (bonjour_sdref) |
1947 | | close(DNSServiceRefSockFD(bonjour_sdref)); |
1948 | | #endif |
1949 | 0 | } |
1950 | | |
1951 | | |
1952 | | /* |
1953 | | * InitProcessGlobals -- set MyStartTime[stamp], random seeds |
1954 | | * |
1955 | | * Called early in the postmaster and every backend. |
1956 | | */ |
1957 | | void |
1958 | | InitProcessGlobals(void) |
1959 | 0 | { |
1960 | 0 | MyStartTimestamp = GetCurrentTimestamp(); |
1961 | 0 | MyStartTime = timestamptz_to_time_t(MyStartTimestamp); |
1962 | | |
1963 | | /* initialize timing infrastructure (required for INSTR_* calls) */ |
1964 | 0 | pg_initialize_timing(); |
1965 | | |
1966 | | /* |
1967 | | * Set a different global seed in every process. We want something |
1968 | | * unpredictable, so if possible, use high-quality random bits for the |
1969 | | * seed. Otherwise, fall back to a seed based on timestamp and PID. |
1970 | | */ |
1971 | 0 | if (unlikely(!pg_prng_strong_seed(&pg_global_prng_state))) |
1972 | 0 | { |
1973 | 0 | uint64 rseed; |
1974 | | |
1975 | | /* |
1976 | | * Since PIDs and timestamps tend to change more frequently in their |
1977 | | * least significant bits, shift the timestamp left to allow a larger |
1978 | | * total number of seeds in a given time period. Since that would |
1979 | | * leave only 20 bits of the timestamp that cycle every ~1 second, |
1980 | | * also mix in some higher bits. |
1981 | | */ |
1982 | 0 | rseed = ((uint64) MyProcPid) ^ |
1983 | 0 | ((uint64) MyStartTimestamp << 12) ^ |
1984 | 0 | ((uint64) MyStartTimestamp >> 20); |
1985 | |
|
1986 | 0 | pg_prng_seed(&pg_global_prng_state, rseed); |
1987 | 0 | } |
1988 | | |
1989 | | /* |
1990 | | * Also make sure that we've set a good seed for random(3). Use of that |
1991 | | * is deprecated in core Postgres, but extensions might use it. |
1992 | | */ |
1993 | 0 | #ifndef WIN32 |
1994 | 0 | srandom(pg_prng_uint32(&pg_global_prng_state)); |
1995 | 0 | #endif |
1996 | 0 | } |
1997 | | |
1998 | | /* |
1999 | | * Child processes use SIGUSR1 to notify us of 'pmsignals'. pg_ctl uses |
2000 | | * SIGUSR1 to ask postmaster to check for logrotate and promote files. |
2001 | | */ |
2002 | | static void |
2003 | | handle_pm_pmsignal_signal(SIGNAL_ARGS) |
2004 | 0 | { |
2005 | 0 | pending_pm_pmsignal = true; |
2006 | 0 | SetLatch(MyLatch); |
2007 | 0 | } |
2008 | | |
2009 | | /* |
2010 | | * pg_ctl uses SIGHUP to request a reload of the configuration files. |
2011 | | */ |
2012 | | static void |
2013 | | handle_pm_reload_request_signal(SIGNAL_ARGS) |
2014 | 0 | { |
2015 | 0 | pending_pm_reload_request = true; |
2016 | 0 | SetLatch(MyLatch); |
2017 | 0 | } |
2018 | | |
2019 | | /* |
2020 | | * Re-read config files, and tell children to do same. |
2021 | | */ |
2022 | | static void |
2023 | | process_pm_reload_request(void) |
2024 | | { |
2025 | | pending_pm_reload_request = false; |
2026 | | |
2027 | | ereport(DEBUG2, |
2028 | | (errmsg_internal("postmaster received reload request signal"))); |
2029 | | |
2030 | | if (Shutdown <= SmartShutdown) |
2031 | | { |
2032 | | ereport(LOG, |
2033 | | (errmsg("received SIGHUP, reloading configuration files"))); |
2034 | | ProcessConfigFile(PGC_SIGHUP); |
2035 | | SignalChildren(SIGHUP, btmask_all_except(B_DEAD_END_BACKEND)); |
2036 | | |
2037 | | /* Reload authentication config files too */ |
2038 | | if (!load_hba()) |
2039 | | ereport(LOG, |
2040 | | /* translator: %s is a configuration file */ |
2041 | | (errmsg("%s was not reloaded", HbaFileName))); |
2042 | | |
2043 | | if (!load_ident()) |
2044 | | ereport(LOG, |
2045 | | (errmsg("%s was not reloaded", IdentFileName))); |
2046 | | |
2047 | | #ifdef USE_SSL |
2048 | | /* Reload SSL configuration as well */ |
2049 | | if (EnableSSL) |
2050 | | { |
2051 | | if (secure_initialize(false) == 0) |
2052 | | LoadedSSL = true; |
2053 | | else |
2054 | | ereport(LOG, |
2055 | | (errmsg("SSL configuration was not reloaded"))); |
2056 | | } |
2057 | | else |
2058 | | { |
2059 | | secure_destroy(); |
2060 | | LoadedSSL = false; |
2061 | | } |
2062 | | #endif |
2063 | | |
2064 | | #ifdef EXEC_BACKEND |
2065 | | /* Update the starting-point file for future children */ |
2066 | | write_nondefault_variables(PGC_SIGHUP); |
2067 | | #endif |
2068 | | } |
2069 | | } |
2070 | | |
2071 | | /* |
2072 | | * pg_ctl uses SIGTERM, SIGINT and SIGQUIT to request different types of |
2073 | | * shutdown. |
2074 | | */ |
2075 | | static void |
2076 | | handle_pm_shutdown_request_signal(SIGNAL_ARGS) |
2077 | 0 | { |
2078 | 0 | switch (postgres_signal_arg) |
2079 | 0 | { |
2080 | 0 | case SIGTERM: |
2081 | | /* smart is implied if the other two flags aren't set */ |
2082 | 0 | pending_pm_shutdown_request = true; |
2083 | 0 | break; |
2084 | 0 | case SIGINT: |
2085 | 0 | pending_pm_fast_shutdown_request = true; |
2086 | 0 | pending_pm_shutdown_request = true; |
2087 | 0 | break; |
2088 | 0 | case SIGQUIT: |
2089 | 0 | pending_pm_immediate_shutdown_request = true; |
2090 | 0 | pending_pm_shutdown_request = true; |
2091 | 0 | break; |
2092 | 0 | } |
2093 | 0 | SetLatch(MyLatch); |
2094 | 0 | } |
2095 | | |
2096 | | /* |
2097 | | * Process shutdown request. |
2098 | | */ |
2099 | | static void |
2100 | | process_pm_shutdown_request(void) |
2101 | | { |
2102 | | int mode; |
2103 | | |
2104 | | ereport(DEBUG2, |
2105 | | (errmsg_internal("postmaster received shutdown request signal"))); |
2106 | | |
2107 | | pending_pm_shutdown_request = false; |
2108 | | |
2109 | | /* |
2110 | | * If more than one shutdown request signal arrived since the last server |
2111 | | * loop, take the one that is the most immediate. That matches the |
2112 | | * priority that would apply if we processed them one by one in any order. |
2113 | | */ |
2114 | | if (pending_pm_immediate_shutdown_request) |
2115 | | { |
2116 | | pending_pm_immediate_shutdown_request = false; |
2117 | | pending_pm_fast_shutdown_request = false; |
2118 | | mode = ImmediateShutdown; |
2119 | | } |
2120 | | else if (pending_pm_fast_shutdown_request) |
2121 | | { |
2122 | | pending_pm_fast_shutdown_request = false; |
2123 | | mode = FastShutdown; |
2124 | | } |
2125 | | else |
2126 | | mode = SmartShutdown; |
2127 | | |
2128 | | switch (mode) |
2129 | | { |
2130 | | case SmartShutdown: |
2131 | | |
2132 | | /* |
2133 | | * Smart Shutdown: |
2134 | | * |
2135 | | * Wait for children to end their work, then shut down. |
2136 | | */ |
2137 | | if (Shutdown >= SmartShutdown) |
2138 | | break; |
2139 | | Shutdown = SmartShutdown; |
2140 | | ereport(LOG, |
2141 | | (errmsg("received smart shutdown request"))); |
2142 | | |
2143 | | /* Report status */ |
2144 | | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STOPPING); |
2145 | | #ifdef USE_SYSTEMD |
2146 | | sd_notify(0, "STOPPING=1"); |
2147 | | #endif |
2148 | | |
2149 | | /* |
2150 | | * If we reached normal running, we go straight to waiting for |
2151 | | * client backends to exit. If already in PM_STOP_BACKENDS or a |
2152 | | * later state, do not change it. |
2153 | | */ |
2154 | | if (pmState == PM_RUN || pmState == PM_HOT_STANDBY) |
2155 | | connsAllowed = false; |
2156 | | else if (pmState == PM_STARTUP || pmState == PM_RECOVERY) |
2157 | | { |
2158 | | /* There should be no clients, so proceed to stop children */ |
2159 | | UpdatePMState(PM_STOP_BACKENDS); |
2160 | | } |
2161 | | |
2162 | | /* |
2163 | | * Now wait for online backup mode to end and backends to exit. If |
2164 | | * that is already the case, PostmasterStateMachine will take the |
2165 | | * next step. |
2166 | | */ |
2167 | | PostmasterStateMachine(); |
2168 | | break; |
2169 | | |
2170 | | case FastShutdown: |
2171 | | |
2172 | | /* |
2173 | | * Fast Shutdown: |
2174 | | * |
2175 | | * Abort all children with SIGTERM (rollback active transactions |
2176 | | * and exit) and shut down when they are gone. |
2177 | | */ |
2178 | | if (Shutdown >= FastShutdown) |
2179 | | break; |
2180 | | Shutdown = FastShutdown; |
2181 | | ereport(LOG, |
2182 | | (errmsg("received fast shutdown request"))); |
2183 | | |
2184 | | /* Report status */ |
2185 | | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STOPPING); |
2186 | | #ifdef USE_SYSTEMD |
2187 | | sd_notify(0, "STOPPING=1"); |
2188 | | #endif |
2189 | | |
2190 | | if (pmState == PM_STARTUP || pmState == PM_RECOVERY) |
2191 | | { |
2192 | | /* Just shut down background processes silently */ |
2193 | | UpdatePMState(PM_STOP_BACKENDS); |
2194 | | } |
2195 | | else if (pmState == PM_RUN || |
2196 | | pmState == PM_HOT_STANDBY) |
2197 | | { |
2198 | | /* Report that we're about to zap live client sessions */ |
2199 | | ereport(LOG, |
2200 | | (errmsg("aborting any active transactions"))); |
2201 | | UpdatePMState(PM_STOP_BACKENDS); |
2202 | | } |
2203 | | |
2204 | | /* |
2205 | | * PostmasterStateMachine will issue any necessary signals, or |
2206 | | * take the next step if no child processes need to be killed. |
2207 | | */ |
2208 | | PostmasterStateMachine(); |
2209 | | break; |
2210 | | |
2211 | | case ImmediateShutdown: |
2212 | | |
2213 | | /* |
2214 | | * Immediate Shutdown: |
2215 | | * |
2216 | | * abort all children with SIGQUIT, wait for them to exit, |
2217 | | * terminate remaining ones with SIGKILL, then exit without |
2218 | | * attempt to properly shut down the data base system. |
2219 | | */ |
2220 | | if (Shutdown >= ImmediateShutdown) |
2221 | | break; |
2222 | | Shutdown = ImmediateShutdown; |
2223 | | ereport(LOG, |
2224 | | (errmsg("received immediate shutdown request"))); |
2225 | | |
2226 | | /* Report status */ |
2227 | | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STOPPING); |
2228 | | #ifdef USE_SYSTEMD |
2229 | | sd_notify(0, "STOPPING=1"); |
2230 | | #endif |
2231 | | |
2232 | | /* tell children to shut down ASAP */ |
2233 | | /* (note we don't apply send_abort_for_crash here) */ |
2234 | | SetQuitSignalReason(PMQUIT_FOR_STOP); |
2235 | | TerminateChildren(SIGQUIT); |
2236 | | UpdatePMState(PM_WAIT_BACKENDS); |
2237 | | |
2238 | | /* set stopwatch for them to die */ |
2239 | | AbortStartTime = time(NULL); |
2240 | | |
2241 | | /* |
2242 | | * Now wait for backends to exit. If there are none, |
2243 | | * PostmasterStateMachine will take the next step. |
2244 | | */ |
2245 | | PostmasterStateMachine(); |
2246 | | break; |
2247 | | } |
2248 | | } |
2249 | | |
2250 | | static void |
2251 | | handle_pm_child_exit_signal(SIGNAL_ARGS) |
2252 | 0 | { |
2253 | 0 | pending_pm_child_exit = true; |
2254 | 0 | SetLatch(MyLatch); |
2255 | 0 | } |
2256 | | |
2257 | | /* |
2258 | | * Cleanup after a child process dies. |
2259 | | */ |
2260 | | static void |
2261 | | process_pm_child_exit(void) |
2262 | 0 | { |
2263 | 0 | int pid; /* process id of dead child process */ |
2264 | 0 | int exitstatus; /* its exit status */ |
2265 | |
|
2266 | 0 | pending_pm_child_exit = false; |
2267 | |
|
2268 | 0 | ereport(DEBUG4, |
2269 | 0 | (errmsg_internal("reaping dead processes"))); |
2270 | | |
2271 | 0 | while ((pid = waitpid(-1, &exitstatus, WNOHANG)) > 0) |
2272 | 0 | { |
2273 | 0 | PMChild *pmchild; |
2274 | | |
2275 | | /* |
2276 | | * Check if this child was a startup process. |
2277 | | */ |
2278 | 0 | if (StartupPMChild && pid == StartupPMChild->pid) |
2279 | 0 | { |
2280 | 0 | ReleasePostmasterChildSlot(StartupPMChild); |
2281 | 0 | StartupPMChild = NULL; |
2282 | | |
2283 | | /* |
2284 | | * Startup process exited in response to a shutdown request (or it |
2285 | | * completed normally regardless of the shutdown request). |
2286 | | */ |
2287 | 0 | if (Shutdown > NoShutdown && |
2288 | 0 | (EXIT_STATUS_0(exitstatus) || EXIT_STATUS_1(exitstatus))) |
2289 | 0 | { |
2290 | 0 | StartupStatus = STARTUP_NOT_RUNNING; |
2291 | 0 | UpdatePMState(PM_WAIT_BACKENDS); |
2292 | | /* PostmasterStateMachine logic does the rest */ |
2293 | 0 | continue; |
2294 | 0 | } |
2295 | | |
2296 | 0 | if (EXIT_STATUS_3(exitstatus)) |
2297 | 0 | { |
2298 | 0 | ereport(LOG, |
2299 | 0 | (errmsg("shutdown at recovery target"))); |
2300 | 0 | StartupStatus = STARTUP_NOT_RUNNING; |
2301 | 0 | Shutdown = Max(Shutdown, SmartShutdown); |
2302 | 0 | TerminateChildren(SIGTERM); |
2303 | 0 | UpdatePMState(PM_WAIT_BACKENDS); |
2304 | | /* PostmasterStateMachine logic does the rest */ |
2305 | 0 | continue; |
2306 | 0 | } |
2307 | | |
2308 | | /* |
2309 | | * Any unexpected exit (including FATAL exit) of the startup |
2310 | | * process is catastrophic, so kill other children, and set |
2311 | | * StartupStatus so we don't try to reinitialize after they're |
2312 | | * gone. Exception: if StartupStatus is STARTUP_SIGNALED, then we |
2313 | | * previously sent the startup process a SIGQUIT; so that's |
2314 | | * probably the reason it died, and we do want to try to restart |
2315 | | * in that case. |
2316 | | * |
2317 | | * This stanza also handles the case where we sent a SIGQUIT |
2318 | | * during PM_STARTUP due to some dead-end child crashing: in that |
2319 | | * situation, if the startup process dies on the SIGQUIT, we need |
2320 | | * to transition to PM_WAIT_BACKENDS state which will allow |
2321 | | * PostmasterStateMachine to restart the startup process. (On the |
2322 | | * other hand, the startup process might complete normally, if we |
2323 | | * were too late with the SIGQUIT. In that case we'll fall |
2324 | | * through and commence normal operations.) |
2325 | | */ |
2326 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2327 | 0 | { |
2328 | 0 | if (StartupStatus == STARTUP_SIGNALED) |
2329 | 0 | { |
2330 | 0 | StartupStatus = STARTUP_NOT_RUNNING; |
2331 | 0 | if (pmState == PM_STARTUP) |
2332 | 0 | UpdatePMState(PM_WAIT_BACKENDS); |
2333 | 0 | } |
2334 | 0 | else |
2335 | 0 | StartupStatus = STARTUP_CRASHED; |
2336 | 0 | HandleChildCrash(pid, exitstatus, |
2337 | 0 | _("startup process")); |
2338 | 0 | continue; |
2339 | 0 | } |
2340 | | |
2341 | | /* |
2342 | | * Startup succeeded, commence normal operations |
2343 | | */ |
2344 | 0 | StartupStatus = STARTUP_NOT_RUNNING; |
2345 | 0 | FatalError = false; |
2346 | 0 | AbortStartTime = 0; |
2347 | 0 | ReachedNormalRunning = true; |
2348 | 0 | UpdatePMState(PM_RUN); |
2349 | 0 | connsAllowed = true; |
2350 | | |
2351 | | /* |
2352 | | * At the next iteration of the postmaster's main loop, we will |
2353 | | * crank up the background tasks like the autovacuum launcher and |
2354 | | * background workers that were not started earlier already. |
2355 | | */ |
2356 | 0 | StartWorkerNeeded = true; |
2357 | | |
2358 | | /* at this point we are really open for business */ |
2359 | 0 | ereport(LOG, |
2360 | 0 | (errmsg("database system is ready to accept connections"))); |
2361 | | |
2362 | | /* Report status */ |
2363 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_READY); |
2364 | | #ifdef USE_SYSTEMD |
2365 | | sd_notify(0, "READY=1"); |
2366 | | #endif |
2367 | |
|
2368 | 0 | continue; |
2369 | 0 | } |
2370 | | |
2371 | | /* |
2372 | | * Was it the bgwriter? Normal exit can be ignored; we'll start a new |
2373 | | * one at the next iteration of the postmaster's main loop, if |
2374 | | * necessary. Any other exit condition is treated as a crash. |
2375 | | */ |
2376 | 0 | if (BgWriterPMChild && pid == BgWriterPMChild->pid) |
2377 | 0 | { |
2378 | 0 | ReleasePostmasterChildSlot(BgWriterPMChild); |
2379 | 0 | BgWriterPMChild = NULL; |
2380 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2381 | 0 | HandleChildCrash(pid, exitstatus, |
2382 | 0 | _("background writer process")); |
2383 | 0 | continue; |
2384 | 0 | } |
2385 | | |
2386 | | /* |
2387 | | * Was it the checkpointer? |
2388 | | */ |
2389 | 0 | if (CheckpointerPMChild && pid == CheckpointerPMChild->pid) |
2390 | 0 | { |
2391 | 0 | ReleasePostmasterChildSlot(CheckpointerPMChild); |
2392 | 0 | CheckpointerPMChild = NULL; |
2393 | 0 | if (EXIT_STATUS_0(exitstatus) && pmState == PM_WAIT_CHECKPOINTER) |
2394 | 0 | { |
2395 | | /* |
2396 | | * OK, we saw normal exit of the checkpointer after it's been |
2397 | | * told to shut down. We know checkpointer wrote a shutdown |
2398 | | * checkpoint, otherwise we'd still be in |
2399 | | * PM_WAIT_XLOG_SHUTDOWN state. |
2400 | | * |
2401 | | * At this point only dead-end children and logger should be |
2402 | | * left. |
2403 | | */ |
2404 | 0 | UpdatePMState(PM_WAIT_DEAD_END); |
2405 | 0 | ConfigurePostmasterWaitSet(false); |
2406 | 0 | SignalChildren(SIGTERM, btmask_all_except(B_LOGGER)); |
2407 | 0 | } |
2408 | 0 | else |
2409 | 0 | { |
2410 | | /* |
2411 | | * Any unexpected exit of the checkpointer (including FATAL |
2412 | | * exit) is treated as a crash. |
2413 | | */ |
2414 | 0 | HandleChildCrash(pid, exitstatus, |
2415 | 0 | _("checkpointer process")); |
2416 | 0 | } |
2417 | |
|
2418 | 0 | continue; |
2419 | 0 | } |
2420 | | |
2421 | | /* |
2422 | | * Was it the wal writer? Normal exit can be ignored; we'll start a |
2423 | | * new one at the next iteration of the postmaster's main loop, if |
2424 | | * necessary. Any other exit condition is treated as a crash. |
2425 | | */ |
2426 | 0 | if (WalWriterPMChild && pid == WalWriterPMChild->pid) |
2427 | 0 | { |
2428 | 0 | ReleasePostmasterChildSlot(WalWriterPMChild); |
2429 | 0 | WalWriterPMChild = NULL; |
2430 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2431 | 0 | HandleChildCrash(pid, exitstatus, |
2432 | 0 | _("WAL writer process")); |
2433 | 0 | continue; |
2434 | 0 | } |
2435 | | |
2436 | | /* |
2437 | | * Was it the wal receiver? If exit status is zero (normal) or one |
2438 | | * (FATAL exit), we assume everything is all right just like normal |
2439 | | * backends. (If we need a new wal receiver, we'll start one at the |
2440 | | * next iteration of the postmaster's main loop.) |
2441 | | */ |
2442 | 0 | if (WalReceiverPMChild && pid == WalReceiverPMChild->pid) |
2443 | 0 | { |
2444 | 0 | ReleasePostmasterChildSlot(WalReceiverPMChild); |
2445 | 0 | WalReceiverPMChild = NULL; |
2446 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2447 | 0 | HandleChildCrash(pid, exitstatus, |
2448 | 0 | _("WAL receiver process")); |
2449 | 0 | continue; |
2450 | 0 | } |
2451 | | |
2452 | | /* |
2453 | | * Was it the wal summarizer? Normal exit can be ignored; we'll start |
2454 | | * a new one at the next iteration of the postmaster's main loop, if |
2455 | | * necessary. Any other exit condition is treated as a crash. |
2456 | | */ |
2457 | 0 | if (WalSummarizerPMChild && pid == WalSummarizerPMChild->pid) |
2458 | 0 | { |
2459 | 0 | ReleasePostmasterChildSlot(WalSummarizerPMChild); |
2460 | 0 | WalSummarizerPMChild = NULL; |
2461 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2462 | 0 | HandleChildCrash(pid, exitstatus, |
2463 | 0 | _("WAL summarizer process")); |
2464 | 0 | continue; |
2465 | 0 | } |
2466 | | |
2467 | | /* |
2468 | | * Was it the autovacuum launcher? Normal exit can be ignored; we'll |
2469 | | * start a new one at the next iteration of the postmaster's main |
2470 | | * loop, if necessary. Any other exit condition is treated as a |
2471 | | * crash. |
2472 | | */ |
2473 | 0 | if (AutoVacLauncherPMChild && pid == AutoVacLauncherPMChild->pid) |
2474 | 0 | { |
2475 | 0 | ReleasePostmasterChildSlot(AutoVacLauncherPMChild); |
2476 | 0 | AutoVacLauncherPMChild = NULL; |
2477 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2478 | 0 | HandleChildCrash(pid, exitstatus, |
2479 | 0 | _("autovacuum launcher process")); |
2480 | 0 | continue; |
2481 | 0 | } |
2482 | | |
2483 | | /* |
2484 | | * Was it the archiver? If exit status is zero (normal) or one (FATAL |
2485 | | * exit), we assume everything is all right just like normal backends |
2486 | | * and just try to start a new one on the next cycle of the |
2487 | | * postmaster's main loop, to retry archiving remaining files. |
2488 | | */ |
2489 | 0 | if (PgArchPMChild && pid == PgArchPMChild->pid) |
2490 | 0 | { |
2491 | 0 | ReleasePostmasterChildSlot(PgArchPMChild); |
2492 | 0 | PgArchPMChild = NULL; |
2493 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2494 | 0 | HandleChildCrash(pid, exitstatus, |
2495 | 0 | _("archiver process")); |
2496 | 0 | continue; |
2497 | 0 | } |
2498 | | |
2499 | | /* Was it the system logger? If so, try to start a new one */ |
2500 | 0 | if (SysLoggerPMChild && pid == SysLoggerPMChild->pid) |
2501 | 0 | { |
2502 | 0 | ReleasePostmasterChildSlot(SysLoggerPMChild); |
2503 | 0 | SysLoggerPMChild = NULL; |
2504 | | |
2505 | | /* for safety's sake, launch new logger *first* */ |
2506 | 0 | if (Logging_collector) |
2507 | 0 | StartSysLogger(); |
2508 | |
|
2509 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2510 | 0 | LogChildExit(LOG, _("system logger process"), |
2511 | 0 | pid, exitstatus); |
2512 | 0 | continue; |
2513 | 0 | } |
2514 | | |
2515 | | /* |
2516 | | * Was it the slot sync worker? Normal exit or FATAL exit can be |
2517 | | * ignored (FATAL can be caused by libpqwalreceiver on receiving |
2518 | | * shutdown request by the startup process during promotion); we'll |
2519 | | * start a new one at the next iteration of the postmaster's main |
2520 | | * loop, if necessary. Any other exit condition is treated as a crash. |
2521 | | */ |
2522 | 0 | if (SlotSyncWorkerPMChild && pid == SlotSyncWorkerPMChild->pid) |
2523 | 0 | { |
2524 | 0 | ReleasePostmasterChildSlot(SlotSyncWorkerPMChild); |
2525 | 0 | SlotSyncWorkerPMChild = NULL; |
2526 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2527 | 0 | HandleChildCrash(pid, exitstatus, |
2528 | 0 | _("slot sync worker process")); |
2529 | 0 | continue; |
2530 | 0 | } |
2531 | | |
2532 | | /* Was it an IO worker? */ |
2533 | 0 | if (maybe_reap_io_worker(pid)) |
2534 | 0 | { |
2535 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2536 | 0 | HandleChildCrash(pid, exitstatus, _("io worker")); |
2537 | | |
2538 | | /* |
2539 | | * A worker that exited with an error might have brought the pool |
2540 | | * size below io_min_workers, or allowed the queue to grow to the |
2541 | | * point where another worker called for growth. |
2542 | | * |
2543 | | * In the common case that a worker timed out due to idleness, no |
2544 | | * replacement needs to be started. maybe_start_io_workers() will |
2545 | | * figure that out. |
2546 | | */ |
2547 | 0 | maybe_start_io_workers(); |
2548 | |
|
2549 | 0 | continue; |
2550 | 0 | } |
2551 | | |
2552 | | /* |
2553 | | * Was it a backend or a background worker? |
2554 | | */ |
2555 | 0 | pmchild = FindPostmasterChildByPid(pid); |
2556 | 0 | if (pmchild) |
2557 | 0 | { |
2558 | 0 | CleanupBackend(pmchild, exitstatus); |
2559 | 0 | } |
2560 | | |
2561 | | /* |
2562 | | * We don't know anything about this child process. That's highly |
2563 | | * unexpected, as we do track all the child processes that we fork. |
2564 | | */ |
2565 | 0 | else |
2566 | 0 | { |
2567 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2568 | 0 | HandleChildCrash(pid, exitstatus, _("untracked child process")); |
2569 | 0 | else |
2570 | 0 | LogChildExit(LOG, _("untracked child process"), pid, exitstatus); |
2571 | 0 | } |
2572 | 0 | } /* loop over pending child-death reports */ |
2573 | | |
2574 | | /* |
2575 | | * After cleaning out the SIGCHLD queue, see if we have any state changes |
2576 | | * or actions to make. |
2577 | | */ |
2578 | 0 | PostmasterStateMachine(); |
2579 | 0 | } |
2580 | | |
2581 | | /* |
2582 | | * CleanupBackend -- cleanup after terminated backend or background worker. |
2583 | | * |
2584 | | * Remove all local state associated with the child process and release its |
2585 | | * PMChild slot. |
2586 | | */ |
2587 | | static void |
2588 | | CleanupBackend(PMChild *bp, |
2589 | | int exitstatus) /* child's exit status. */ |
2590 | 0 | { |
2591 | 0 | char namebuf[MAXPGPATH]; |
2592 | 0 | const char *procname; |
2593 | 0 | bool crashed = false; |
2594 | 0 | bool logged = false; |
2595 | 0 | pid_t bp_pid; |
2596 | 0 | bool bp_bgworker_notify; |
2597 | 0 | BackendType bp_bkend_type; |
2598 | 0 | RegisteredBgWorker *rw; |
2599 | | |
2600 | | /* Construct a process name for the log message */ |
2601 | 0 | if (bp->bkend_type == B_BG_WORKER) |
2602 | 0 | { |
2603 | 0 | snprintf(namebuf, MAXPGPATH, _("background worker \"%s\""), |
2604 | 0 | bp->rw->rw_worker.bgw_type); |
2605 | 0 | procname = namebuf; |
2606 | 0 | } |
2607 | 0 | else |
2608 | 0 | procname = _(GetBackendTypeDesc(bp->bkend_type)); |
2609 | | |
2610 | | /* |
2611 | | * If a backend dies in an ugly way then we must signal all other backends |
2612 | | * to quickdie. If exit status is zero (normal) or one (FATAL exit), we |
2613 | | * assume everything is all right and proceed to remove the backend from |
2614 | | * the active child list. |
2615 | | */ |
2616 | 0 | if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus)) |
2617 | 0 | crashed = true; |
2618 | |
|
2619 | | #ifdef WIN32 |
2620 | | |
2621 | | /* |
2622 | | * On win32, also treat ERROR_WAIT_NO_CHILDREN (128) as nonfatal case, |
2623 | | * since that sometimes happens under load when the process fails to start |
2624 | | * properly (long before it starts using shared memory). Microsoft reports |
2625 | | * it is related to mutex failure: |
2626 | | * http://archives.postgresql.org/pgsql-hackers/2010-09/msg00790.php |
2627 | | */ |
2628 | | if (exitstatus == ERROR_WAIT_NO_CHILDREN) |
2629 | | { |
2630 | | LogChildExit(LOG, procname, bp->pid, exitstatus); |
2631 | | logged = true; |
2632 | | crashed = false; |
2633 | | } |
2634 | | #endif |
2635 | | |
2636 | | /* |
2637 | | * Release the PMChild entry. |
2638 | | * |
2639 | | * If the process attached to shared memory, this also checks that it |
2640 | | * detached cleanly. |
2641 | | */ |
2642 | 0 | bp_pid = bp->pid; |
2643 | 0 | bp_bgworker_notify = bp->bgworker_notify; |
2644 | 0 | bp_bkend_type = bp->bkend_type; |
2645 | 0 | rw = bp->rw; |
2646 | 0 | if (!ReleasePostmasterChildSlot(bp)) |
2647 | 0 | { |
2648 | | /* |
2649 | | * Uh-oh, the child failed to clean itself up. Treat as a crash after |
2650 | | * all. |
2651 | | */ |
2652 | 0 | crashed = true; |
2653 | 0 | } |
2654 | 0 | bp = NULL; |
2655 | | |
2656 | | /* |
2657 | | * In a crash case, exit immediately without resetting background worker |
2658 | | * state. However, if restart_after_crash is enabled, the background |
2659 | | * worker state (e.g., rw_pid) still needs be reset so the worker can |
2660 | | * restart after crash recovery. This reset is handled in |
2661 | | * ResetBackgroundWorkerCrashTimes(), not here. |
2662 | | */ |
2663 | 0 | if (crashed) |
2664 | 0 | { |
2665 | 0 | HandleChildCrash(bp_pid, exitstatus, procname); |
2666 | 0 | return; |
2667 | 0 | } |
2668 | | |
2669 | | /* |
2670 | | * This backend may have been slated to receive SIGUSR1 when some |
2671 | | * background worker started or stopped. Cancel those notifications, as |
2672 | | * we don't want to signal PIDs that are not PostgreSQL backends. This |
2673 | | * gets skipped in the (probably very common) case where the backend has |
2674 | | * never requested any such notifications. |
2675 | | */ |
2676 | 0 | if (bp_bgworker_notify) |
2677 | 0 | BackgroundWorkerStopNotifications(bp_pid); |
2678 | | |
2679 | | /* |
2680 | | * If it was an autovacuum worker, wake up the launcher so that it can |
2681 | | * immediately launch a new worker or rebalance to cost limit setting of |
2682 | | * the remaining workers. |
2683 | | */ |
2684 | 0 | if (bp_bkend_type == B_AUTOVAC_WORKER && AutoVacLauncherPMChild != NULL) |
2685 | 0 | signal_child(AutoVacLauncherPMChild, SIGUSR2); |
2686 | | |
2687 | | /* |
2688 | | * If it was a background worker, also update its RegisteredBgWorker |
2689 | | * entry. |
2690 | | */ |
2691 | 0 | if (bp_bkend_type == B_BG_WORKER) |
2692 | 0 | { |
2693 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2694 | 0 | { |
2695 | | /* Record timestamp, so we know when to restart the worker. */ |
2696 | 0 | rw->rw_crashed_at = GetCurrentTimestamp(); |
2697 | 0 | } |
2698 | 0 | else |
2699 | 0 | { |
2700 | | /* Zero exit status means terminate */ |
2701 | 0 | rw->rw_crashed_at = 0; |
2702 | 0 | rw->rw_terminate = true; |
2703 | 0 | } |
2704 | |
|
2705 | 0 | rw->rw_pid = 0; |
2706 | 0 | ReportBackgroundWorkerExit(rw); /* report child death */ |
2707 | |
|
2708 | 0 | if (!logged) |
2709 | 0 | { |
2710 | 0 | LogChildExit(EXIT_STATUS_0(exitstatus) ? DEBUG1 : LOG, |
2711 | 0 | procname, bp_pid, exitstatus); |
2712 | 0 | logged = true; |
2713 | 0 | } |
2714 | | |
2715 | | /* have it be restarted */ |
2716 | 0 | HaveCrashedWorker = true; |
2717 | 0 | } |
2718 | |
|
2719 | 0 | if (!logged) |
2720 | 0 | LogChildExit(DEBUG2, procname, bp_pid, exitstatus); |
2721 | 0 | } |
2722 | | |
2723 | | /* |
2724 | | * Transition into FatalError state, in response to something bad having |
2725 | | * happened. Commonly the caller will have logged the reason for entering |
2726 | | * FatalError state. |
2727 | | * |
2728 | | * This should only be called when not already in FatalError or |
2729 | | * ImmediateShutdown state. |
2730 | | */ |
2731 | | static void |
2732 | | HandleFatalError(QuitSignalReason reason, bool consider_sigabrt) |
2733 | 0 | { |
2734 | 0 | int sigtosend; |
2735 | |
|
2736 | 0 | Assert(!FatalError); |
2737 | 0 | Assert(Shutdown != ImmediateShutdown); |
2738 | |
|
2739 | 0 | SetQuitSignalReason(reason); |
2740 | |
|
2741 | 0 | if (consider_sigabrt && send_abort_for_crash) |
2742 | 0 | sigtosend = SIGABRT; |
2743 | 0 | else |
2744 | 0 | sigtosend = SIGQUIT; |
2745 | | |
2746 | | /* |
2747 | | * Signal all other child processes to exit. |
2748 | | * |
2749 | | * We could exclude dead-end children here, but at least when sending |
2750 | | * SIGABRT it seems better to include them. |
2751 | | */ |
2752 | 0 | TerminateChildren(sigtosend); |
2753 | |
|
2754 | 0 | FatalError = true; |
2755 | | |
2756 | | /* |
2757 | | * Choose the appropriate new state to react to the fatal error. Unless we |
2758 | | * were already in the process of shutting down, we go through |
2759 | | * PM_WAIT_BACKENDS. For errors during the shutdown sequence, we directly |
2760 | | * switch to PM_WAIT_DEAD_END. |
2761 | | */ |
2762 | 0 | switch (pmState) |
2763 | 0 | { |
2764 | 0 | case PM_INIT: |
2765 | | /* shouldn't have any children */ |
2766 | 0 | Assert(false); |
2767 | 0 | break; |
2768 | | |
2769 | | /* wait for children to die */ |
2770 | 0 | case PM_STARTUP: |
2771 | 0 | case PM_RECOVERY: |
2772 | 0 | case PM_HOT_STANDBY: |
2773 | 0 | case PM_RUN: |
2774 | 0 | case PM_STOP_BACKENDS: |
2775 | 0 | UpdatePMState(PM_WAIT_BACKENDS); |
2776 | 0 | break; |
2777 | | |
2778 | 0 | case PM_WAIT_BACKENDS: |
2779 | | /* there might be more backends to wait for */ |
2780 | 0 | break; |
2781 | | |
2782 | 0 | case PM_WAIT_XLOG_SHUTDOWN: |
2783 | 0 | case PM_WAIT_XLOG_ARCHIVAL: |
2784 | 0 | case PM_WAIT_CHECKPOINTER: |
2785 | 0 | case PM_WAIT_IO_WORKERS: |
2786 | | |
2787 | | /* |
2788 | | * NB: Similar code exists in PostmasterStateMachine()'s handling |
2789 | | * of FatalError in PM_STOP_BACKENDS/PM_WAIT_BACKENDS states. |
2790 | | */ |
2791 | 0 | ConfigurePostmasterWaitSet(false); |
2792 | 0 | UpdatePMState(PM_WAIT_DEAD_END); |
2793 | 0 | break; |
2794 | | |
2795 | 0 | case PM_WAIT_DEAD_END: |
2796 | 0 | case PM_NO_CHILDREN: |
2797 | 0 | break; |
2798 | 0 | } |
2799 | | |
2800 | | /* |
2801 | | * .. and if this doesn't happen quickly enough, now the clock is ticking |
2802 | | * for us to kill them without mercy. |
2803 | | */ |
2804 | 0 | if (AbortStartTime == 0) |
2805 | 0 | AbortStartTime = time(NULL); |
2806 | 0 | } |
2807 | | |
2808 | | /* |
2809 | | * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer, |
2810 | | * walwriter, autovacuum, archiver, slot sync worker, or background worker. |
2811 | | * |
2812 | | * The objectives here are to clean up our local state about the child |
2813 | | * process, and to signal all other remaining children to quickdie. |
2814 | | * |
2815 | | * The caller has already released its PMChild slot. |
2816 | | */ |
2817 | | static void |
2818 | | HandleChildCrash(int pid, int exitstatus, const char *procname) |
2819 | | { |
2820 | | /* |
2821 | | * We only log messages and send signals if this is the first process |
2822 | | * crash and we're not doing an immediate shutdown; otherwise, we're only |
2823 | | * here to update postmaster's idea of live processes. If we have already |
2824 | | * signaled children, nonzero exit status is to be expected, so don't |
2825 | | * clutter log. |
2826 | | */ |
2827 | | if (FatalError || Shutdown == ImmediateShutdown) |
2828 | | return; |
2829 | | |
2830 | | LogChildExit(LOG, procname, pid, exitstatus); |
2831 | | ereport(LOG, |
2832 | | (errmsg("terminating any other active server processes"))); |
2833 | | |
2834 | | /* |
2835 | | * Switch into error state. The crashed process has already been removed |
2836 | | * from ActiveChildList. |
2837 | | */ |
2838 | | HandleFatalError(PMQUIT_FOR_CRASH, true); |
2839 | | } |
2840 | | |
2841 | | /* |
2842 | | * Log the death of a child process. |
2843 | | */ |
2844 | | static void |
2845 | | LogChildExit(int lev, const char *procname, int pid, int exitstatus) |
2846 | 0 | { |
2847 | | /* |
2848 | | * size of activity_buffer is arbitrary, but set equal to default |
2849 | | * track_activity_query_size |
2850 | | */ |
2851 | 0 | char activity_buffer[1024]; |
2852 | 0 | const char *activity = NULL; |
2853 | |
|
2854 | 0 | if (!EXIT_STATUS_0(exitstatus)) |
2855 | 0 | activity = pgstat_get_crashed_backend_activity(pid, |
2856 | 0 | activity_buffer, |
2857 | 0 | sizeof(activity_buffer)); |
2858 | |
|
2859 | 0 | if (WIFEXITED(exitstatus)) |
2860 | 0 | ereport(lev, |
2861 | | |
2862 | | /*------ |
2863 | | translator: %s is a noun phrase describing a child process, such as |
2864 | | "server process" */ |
2865 | 0 | (errmsg("%s (PID %d) exited with exit code %d", |
2866 | 0 | procname, pid, WEXITSTATUS(exitstatus)), |
2867 | 0 | activity ? errdetail("Failed process was running: %s", activity) : 0)); |
2868 | 0 | else if (WIFSIGNALED(exitstatus)) |
2869 | 0 | { |
2870 | | #if defined(WIN32) |
2871 | | ereport(lev, |
2872 | | |
2873 | | /*------ |
2874 | | translator: %s is a noun phrase describing a child process, such as |
2875 | | "server process" */ |
2876 | | (errmsg("%s (PID %d) was terminated by exception 0x%X", |
2877 | | procname, pid, WTERMSIG(exitstatus)), |
2878 | | errhint("See C include file \"ntstatus.h\" for a description of the hexadecimal value."), |
2879 | | activity ? errdetail("Failed process was running: %s", activity) : 0)); |
2880 | | #else |
2881 | 0 | ereport(lev, |
2882 | | |
2883 | | /*------ |
2884 | | translator: %s is a noun phrase describing a child process, such as |
2885 | | "server process" */ |
2886 | 0 | (errmsg("%s (PID %d) was terminated by signal %d: %s", |
2887 | 0 | procname, pid, WTERMSIG(exitstatus), |
2888 | 0 | pg_strsignal(WTERMSIG(exitstatus))), |
2889 | 0 | activity ? errdetail("Failed process was running: %s", activity) : 0)); |
2890 | 0 | #endif |
2891 | 0 | } |
2892 | 0 | else |
2893 | 0 | ereport(lev, |
2894 | | |
2895 | | /*------ |
2896 | | translator: %s is a noun phrase describing a child process, such as |
2897 | | "server process" */ |
2898 | 0 | (errmsg("%s (PID %d) exited with unrecognized status %d", |
2899 | 0 | procname, pid, exitstatus), |
2900 | 0 | activity ? errdetail("Failed process was running: %s", activity) : 0)); |
2901 | 0 | } |
2902 | | |
2903 | | /* |
2904 | | * Advance the postmaster's state machine and take actions as appropriate |
2905 | | * |
2906 | | * This is common code for process_pm_shutdown_request(), |
2907 | | * process_pm_child_exit() and process_pm_pmsignal(), which process the signals |
2908 | | * that might mean we need to change state. |
2909 | | */ |
2910 | | static void |
2911 | | PostmasterStateMachine(void) |
2912 | 0 | { |
2913 | | /* If we're doing a smart shutdown, try to advance that state. */ |
2914 | 0 | if (pmState == PM_RUN || pmState == PM_HOT_STANDBY) |
2915 | 0 | { |
2916 | 0 | if (!connsAllowed) |
2917 | 0 | { |
2918 | | /* |
2919 | | * This state ends when we have no normal client backends running. |
2920 | | * Then we're ready to stop other children. |
2921 | | */ |
2922 | 0 | if (CountChildren(btmask(B_BACKEND)) == 0) |
2923 | 0 | UpdatePMState(PM_STOP_BACKENDS); |
2924 | 0 | } |
2925 | 0 | } |
2926 | | |
2927 | | /* |
2928 | | * In the PM_WAIT_BACKENDS state, wait for all the regular backends and |
2929 | | * processes like autovacuum and background workers that are comparable to |
2930 | | * backends to exit. |
2931 | | * |
2932 | | * PM_STOP_BACKENDS is a transient state that means the same as |
2933 | | * PM_WAIT_BACKENDS, but we signal the processes first, before waiting for |
2934 | | * them. Treating it as a distinct pmState allows us to share this code |
2935 | | * across multiple shutdown code paths. |
2936 | | */ |
2937 | 0 | if (pmState == PM_STOP_BACKENDS || pmState == PM_WAIT_BACKENDS) |
2938 | 0 | { |
2939 | 0 | BackendTypeMask targetMask = BTYPE_MASK_NONE; |
2940 | | |
2941 | | /* |
2942 | | * PM_WAIT_BACKENDS state ends when we have no regular backends, no |
2943 | | * autovac launcher or workers, and no bgworkers (including |
2944 | | * unconnected ones). |
2945 | | */ |
2946 | 0 | targetMask = btmask_add(targetMask, |
2947 | 0 | B_BACKEND, |
2948 | 0 | B_AUTOVAC_LAUNCHER, |
2949 | 0 | B_AUTOVAC_WORKER, |
2950 | 0 | B_BG_WORKER); |
2951 | | |
2952 | | /* |
2953 | | * No walwriter, bgwriter, slot sync worker, or WAL summarizer either. |
2954 | | */ |
2955 | 0 | targetMask = btmask_add(targetMask, |
2956 | 0 | B_WAL_WRITER, |
2957 | 0 | B_BG_WRITER, |
2958 | 0 | B_SLOTSYNC_WORKER, |
2959 | 0 | B_WAL_SUMMARIZER); |
2960 | | |
2961 | | /* If we're in recovery, also stop startup and walreceiver procs */ |
2962 | 0 | targetMask = btmask_add(targetMask, |
2963 | 0 | B_STARTUP, |
2964 | 0 | B_WAL_RECEIVER); |
2965 | | |
2966 | | /* |
2967 | | * If we are doing crash recovery or an immediate shutdown then we |
2968 | | * expect archiver, checkpointer, io workers and walsender to exit as |
2969 | | * well, otherwise not. |
2970 | | */ |
2971 | 0 | if (FatalError || Shutdown >= ImmediateShutdown) |
2972 | 0 | targetMask = btmask_add(targetMask, |
2973 | 0 | B_CHECKPOINTER, |
2974 | 0 | B_ARCHIVER, |
2975 | 0 | B_IO_WORKER, |
2976 | 0 | B_WAL_SENDER); |
2977 | | |
2978 | | /* |
2979 | | * Normally archiver, checkpointer, IO workers and walsenders will |
2980 | | * continue running; they will be terminated later after writing the |
2981 | | * checkpoint record. We also let dead-end children to keep running |
2982 | | * for now. The syslogger process exits last. |
2983 | | * |
2984 | | * This assertion checks that we have covered all backend types, |
2985 | | * either by including them in targetMask, or by noting here that they |
2986 | | * are allowed to continue running. |
2987 | | */ |
2988 | | #ifdef USE_ASSERT_CHECKING |
2989 | | { |
2990 | | BackendTypeMask remainMask = BTYPE_MASK_NONE; |
2991 | | |
2992 | | remainMask = btmask_add(remainMask, |
2993 | | B_DEAD_END_BACKEND, |
2994 | | B_LOGGER); |
2995 | | |
2996 | | /* |
2997 | | * Archiver, checkpointer, IO workers, and walsender may or may |
2998 | | * not be in targetMask already. |
2999 | | */ |
3000 | | remainMask = btmask_add(remainMask, |
3001 | | B_ARCHIVER, |
3002 | | B_CHECKPOINTER, |
3003 | | B_IO_WORKER, |
3004 | | B_WAL_SENDER); |
3005 | | |
3006 | | /* these are not real postmaster children */ |
3007 | | remainMask = btmask_add(remainMask, |
3008 | | B_INVALID, |
3009 | | B_STANDALONE_BACKEND); |
3010 | | |
3011 | | /* also add data checksums processes */ |
3012 | | remainMask = btmask_add(remainMask, |
3013 | | B_DATACHECKSUMSWORKER_LAUNCHER, |
3014 | | B_DATACHECKSUMSWORKER_WORKER); |
3015 | | |
3016 | | /* All types should be included in targetMask or remainMask */ |
3017 | | Assert((remainMask.mask | targetMask.mask) == BTYPE_MASK_ALL.mask); |
3018 | | } |
3019 | | #endif |
3020 | | |
3021 | | /* If we had not yet signaled the processes to exit, do so now */ |
3022 | 0 | if (pmState == PM_STOP_BACKENDS) |
3023 | 0 | { |
3024 | | /* |
3025 | | * Forget any pending requests for background workers, since we're |
3026 | | * no longer willing to launch any new workers. (If additional |
3027 | | * requests arrive, BackgroundWorkerStateChange will reject them.) |
3028 | | */ |
3029 | 0 | ForgetUnstartedBackgroundWorkers(); |
3030 | |
|
3031 | 0 | SignalChildren(SIGTERM, targetMask); |
3032 | |
|
3033 | 0 | UpdatePMState(PM_WAIT_BACKENDS); |
3034 | 0 | } |
3035 | | |
3036 | | /* Are any of the target processes still running? */ |
3037 | 0 | if (CountChildren(targetMask) == 0) |
3038 | 0 | { |
3039 | 0 | if (Shutdown >= ImmediateShutdown || FatalError) |
3040 | 0 | { |
3041 | | /* |
3042 | | * Stop any dead-end children and stop creating new ones. |
3043 | | * |
3044 | | * NB: Similar code exists in HandleFatalError(), when the |
3045 | | * error happens in pmState > PM_WAIT_BACKENDS. |
3046 | | */ |
3047 | 0 | UpdatePMState(PM_WAIT_DEAD_END); |
3048 | 0 | ConfigurePostmasterWaitSet(false); |
3049 | 0 | SignalChildren(SIGQUIT, btmask(B_DEAD_END_BACKEND)); |
3050 | | |
3051 | | /* |
3052 | | * We already SIGQUIT'd auxiliary processes (other than |
3053 | | * logger), if any, when we started immediate shutdown or |
3054 | | * entered FatalError state. |
3055 | | */ |
3056 | 0 | } |
3057 | 0 | else |
3058 | 0 | { |
3059 | | /* |
3060 | | * If we get here, we are proceeding with normal shutdown. All |
3061 | | * the regular children are gone, and it's time to tell the |
3062 | | * checkpointer to do a shutdown checkpoint. |
3063 | | */ |
3064 | 0 | Assert(Shutdown > NoShutdown); |
3065 | | /* Start the checkpointer if not running */ |
3066 | 0 | if (CheckpointerPMChild == NULL) |
3067 | 0 | CheckpointerPMChild = StartChildProcess(B_CHECKPOINTER); |
3068 | | /* And tell it to write the shutdown checkpoint */ |
3069 | 0 | if (CheckpointerPMChild != NULL) |
3070 | 0 | { |
3071 | 0 | signal_child(CheckpointerPMChild, SIGINT); |
3072 | 0 | UpdatePMState(PM_WAIT_XLOG_SHUTDOWN); |
3073 | 0 | } |
3074 | 0 | else |
3075 | 0 | { |
3076 | | /* |
3077 | | * If we failed to fork a checkpointer, just shut down. |
3078 | | * Any required cleanup will happen at next restart. We |
3079 | | * set FatalError so that an "abnormal shutdown" message |
3080 | | * gets logged when we exit. |
3081 | | * |
3082 | | * We don't consult send_abort_for_crash here, as it's |
3083 | | * unlikely that dumping cores would illuminate the reason |
3084 | | * for checkpointer fork failure. |
3085 | | * |
3086 | | * XXX: It may be worth to introduce a different PMQUIT |
3087 | | * value that signals that the cluster is in a bad state, |
3088 | | * without a process having crashed. But right now this |
3089 | | * path is very unlikely to be reached, so it isn't |
3090 | | * obviously worthwhile adding a distinct error message in |
3091 | | * quickdie(). |
3092 | | */ |
3093 | 0 | HandleFatalError(PMQUIT_FOR_CRASH, false); |
3094 | 0 | } |
3095 | 0 | } |
3096 | 0 | } |
3097 | 0 | } |
3098 | | |
3099 | | /* |
3100 | | * The state transition from PM_WAIT_XLOG_SHUTDOWN to |
3101 | | * PM_WAIT_XLOG_ARCHIVAL is in process_pm_pmsignal(), in response to |
3102 | | * PMSIGNAL_XLOG_IS_SHUTDOWN. |
3103 | | */ |
3104 | |
|
3105 | 0 | if (pmState == PM_WAIT_XLOG_ARCHIVAL) |
3106 | 0 | { |
3107 | | /* |
3108 | | * PM_WAIT_XLOG_ARCHIVAL state ends when there are no children other |
3109 | | * than checkpointer, io workers and dead-end children left. There |
3110 | | * shouldn't be any regular backends left by now anyway; what we're |
3111 | | * really waiting for is for walsenders and archiver to exit. |
3112 | | */ |
3113 | 0 | if (CountChildren(btmask_all_except(B_CHECKPOINTER, B_IO_WORKER, |
3114 | 0 | B_LOGGER, B_DEAD_END_BACKEND)) == 0) |
3115 | 0 | { |
3116 | 0 | UpdatePMState(PM_WAIT_IO_WORKERS); |
3117 | 0 | SignalChildren(SIGUSR2, btmask(B_IO_WORKER)); |
3118 | 0 | } |
3119 | 0 | } |
3120 | |
|
3121 | 0 | if (pmState == PM_WAIT_IO_WORKERS) |
3122 | 0 | { |
3123 | | /* |
3124 | | * PM_WAIT_IO_WORKERS state ends when there's only checkpointer and |
3125 | | * dead-end children left. |
3126 | | */ |
3127 | 0 | if (io_worker_count == 0) |
3128 | 0 | { |
3129 | 0 | UpdatePMState(PM_WAIT_CHECKPOINTER); |
3130 | | |
3131 | | /* |
3132 | | * Now that the processes mentioned above are gone, tell |
3133 | | * checkpointer to shut down too. That allows checkpointer to |
3134 | | * perform some last bits of cleanup without other processes |
3135 | | * interfering. |
3136 | | */ |
3137 | 0 | if (CheckpointerPMChild != NULL) |
3138 | 0 | signal_child(CheckpointerPMChild, SIGUSR2); |
3139 | 0 | } |
3140 | 0 | } |
3141 | | |
3142 | | /* |
3143 | | * The state transition from PM_WAIT_CHECKPOINTER to PM_WAIT_DEAD_END is |
3144 | | * in process_pm_child_exit(). |
3145 | | */ |
3146 | |
|
3147 | 0 | if (pmState == PM_WAIT_DEAD_END) |
3148 | 0 | { |
3149 | | /* |
3150 | | * PM_WAIT_DEAD_END state ends when all other children are gone except |
3151 | | * for the logger. During normal shutdown, all that remains are |
3152 | | * dead-end backends, but in FatalError processing we jump straight |
3153 | | * here with more processes remaining. Note that they have already |
3154 | | * been sent appropriate shutdown signals, either during a normal |
3155 | | * state transition leading up to PM_WAIT_DEAD_END, or during |
3156 | | * FatalError processing. |
3157 | | * |
3158 | | * The reason we wait is to protect against a new postmaster starting |
3159 | | * conflicting subprocesses; this isn't an ironclad protection, but it |
3160 | | * at least helps in the shutdown-and-immediately-restart scenario. |
3161 | | */ |
3162 | 0 | if (CountChildren(btmask_all_except(B_LOGGER)) == 0) |
3163 | 0 | { |
3164 | | /* These other guys should be dead already */ |
3165 | 0 | Assert(StartupPMChild == NULL); |
3166 | 0 | Assert(WalReceiverPMChild == NULL); |
3167 | 0 | Assert(WalSummarizerPMChild == NULL); |
3168 | 0 | Assert(BgWriterPMChild == NULL); |
3169 | 0 | Assert(CheckpointerPMChild == NULL); |
3170 | 0 | Assert(WalWriterPMChild == NULL); |
3171 | 0 | Assert(AutoVacLauncherPMChild == NULL); |
3172 | 0 | Assert(SlotSyncWorkerPMChild == NULL); |
3173 | | /* syslogger is not considered here */ |
3174 | 0 | UpdatePMState(PM_NO_CHILDREN); |
3175 | 0 | } |
3176 | 0 | } |
3177 | | |
3178 | | /* |
3179 | | * If we've been told to shut down, we exit as soon as there are no |
3180 | | * remaining children. If there was a crash, cleanup will occur at the |
3181 | | * next startup. (Before PostgreSQL 8.3, we tried to recover from the |
3182 | | * crash before exiting, but that seems unwise if we are quitting because |
3183 | | * we got SIGTERM from init --- there may well not be time for recovery |
3184 | | * before init decides to SIGKILL us.) |
3185 | | * |
3186 | | * Note that the syslogger continues to run. It will exit when it sees |
3187 | | * EOF on its input pipe, which happens when there are no more upstream |
3188 | | * processes. |
3189 | | */ |
3190 | 0 | if (Shutdown > NoShutdown && pmState == PM_NO_CHILDREN) |
3191 | 0 | { |
3192 | 0 | if (FatalError) |
3193 | 0 | { |
3194 | 0 | ereport(LOG, (errmsg("abnormal database system shutdown"))); |
3195 | 0 | ExitPostmaster(1); |
3196 | 0 | } |
3197 | 0 | else |
3198 | 0 | { |
3199 | | /* |
3200 | | * Normal exit from the postmaster is here. We don't need to log |
3201 | | * anything here, since the UnlinkLockFiles proc_exit callback |
3202 | | * will do so, and that should be the last user-visible action. |
3203 | | */ |
3204 | 0 | ExitPostmaster(0); |
3205 | 0 | } |
3206 | 0 | } |
3207 | | |
3208 | | /* |
3209 | | * If the startup process failed, or the user does not want an automatic |
3210 | | * restart after backend crashes, wait for all non-syslogger children to |
3211 | | * exit, and then exit postmaster. We don't try to reinitialize when the |
3212 | | * startup process fails, because more than likely it will just fail again |
3213 | | * and we will keep trying forever. |
3214 | | */ |
3215 | 0 | if (pmState == PM_NO_CHILDREN) |
3216 | 0 | { |
3217 | 0 | if (StartupStatus == STARTUP_CRASHED) |
3218 | 0 | { |
3219 | 0 | ereport(LOG, |
3220 | 0 | (errmsg("shutting down due to startup process failure"))); |
3221 | 0 | ExitPostmaster(1); |
3222 | 0 | } |
3223 | 0 | if (!restart_after_crash) |
3224 | 0 | { |
3225 | 0 | ereport(LOG, |
3226 | 0 | (errmsg("shutting down because \"restart_after_crash\" is off"))); |
3227 | 0 | ExitPostmaster(1); |
3228 | 0 | } |
3229 | 0 | } |
3230 | | |
3231 | | /* |
3232 | | * If we need to recover from a crash, wait for all non-syslogger children |
3233 | | * to exit, then reset shmem and start the startup process. |
3234 | | */ |
3235 | 0 | if (FatalError && pmState == PM_NO_CHILDREN) |
3236 | 0 | { |
3237 | 0 | ereport(LOG, |
3238 | 0 | (errmsg("all server processes terminated; reinitializing"))); |
3239 | | |
3240 | | /* remove leftover temporary files after a crash */ |
3241 | 0 | if (remove_temp_files_after_crash) |
3242 | 0 | RemovePgTempFiles(); |
3243 | | |
3244 | | /* allow background workers to immediately restart */ |
3245 | 0 | ResetBackgroundWorkerCrashTimes(); |
3246 | |
|
3247 | 0 | shmem_exit(1); |
3248 | | |
3249 | | /* re-read control file into local memory */ |
3250 | 0 | LocalProcessControlFile(true); |
3251 | | |
3252 | | /* |
3253 | | * Re-initialize shared memory and semaphores. Note: We don't call |
3254 | | * RegisterBuiltinShmemCallbacks(), we keep the old registrations. In |
3255 | | * order to re-register structs in extensions, we'd need to reload |
3256 | | * shared preload libraries, and we don't want to do that. |
3257 | | */ |
3258 | 0 | ResetShmemAllocator(); |
3259 | 0 | ShmemCallRequestCallbacks(); |
3260 | 0 | CreateSharedMemoryAndSemaphores(); |
3261 | |
|
3262 | 0 | UpdatePMState(PM_STARTUP); |
3263 | | |
3264 | | /* Make sure we can perform I/O while starting up. */ |
3265 | 0 | maybe_start_io_workers(); |
3266 | |
|
3267 | 0 | StartupPMChild = StartChildProcess(B_STARTUP); |
3268 | 0 | Assert(StartupPMChild != NULL); |
3269 | 0 | StartupStatus = STARTUP_RUNNING; |
3270 | | /* crash recovery started, reset SIGKILL flag */ |
3271 | 0 | AbortStartTime = 0; |
3272 | | |
3273 | | /* start accepting server socket connection events again */ |
3274 | 0 | ConfigurePostmasterWaitSet(true); |
3275 | 0 | } |
3276 | 0 | } |
3277 | | |
3278 | | static const char * |
3279 | | pmstate_name(PMState state) |
3280 | 0 | { |
3281 | 0 | #define PM_TOSTR_CASE(sym) case sym: return #sym |
3282 | 0 | switch (state) |
3283 | 0 | { |
3284 | 0 | PM_TOSTR_CASE(PM_INIT); |
3285 | 0 | PM_TOSTR_CASE(PM_STARTUP); |
3286 | 0 | PM_TOSTR_CASE(PM_RECOVERY); |
3287 | 0 | PM_TOSTR_CASE(PM_HOT_STANDBY); |
3288 | 0 | PM_TOSTR_CASE(PM_RUN); |
3289 | 0 | PM_TOSTR_CASE(PM_STOP_BACKENDS); |
3290 | 0 | PM_TOSTR_CASE(PM_WAIT_BACKENDS); |
3291 | 0 | PM_TOSTR_CASE(PM_WAIT_XLOG_SHUTDOWN); |
3292 | 0 | PM_TOSTR_CASE(PM_WAIT_XLOG_ARCHIVAL); |
3293 | 0 | PM_TOSTR_CASE(PM_WAIT_IO_WORKERS); |
3294 | 0 | PM_TOSTR_CASE(PM_WAIT_DEAD_END); |
3295 | 0 | PM_TOSTR_CASE(PM_WAIT_CHECKPOINTER); |
3296 | 0 | PM_TOSTR_CASE(PM_NO_CHILDREN); |
3297 | 0 | } |
3298 | 0 | #undef PM_TOSTR_CASE |
3299 | | |
3300 | 0 | pg_unreachable(); |
3301 | 0 | return ""; /* silence compiler */ |
3302 | 0 | } |
3303 | | |
3304 | | /* |
3305 | | * Simple wrapper for updating pmState. The main reason to have this wrapper |
3306 | | * is that it makes it easy to log all state transitions. |
3307 | | */ |
3308 | | static void |
3309 | | UpdatePMState(PMState newState) |
3310 | | { |
3311 | | elog(DEBUG1, "updating PMState from %s to %s", |
3312 | | pmstate_name(pmState), pmstate_name(newState)); |
3313 | | pmState = newState; |
3314 | | } |
3315 | | |
3316 | | /* |
3317 | | * Launch background processes after state change, or relaunch after an |
3318 | | * existing process has exited. |
3319 | | * |
3320 | | * Check the current pmState and the status of any background processes. If |
3321 | | * there are any background processes missing that should be running in the |
3322 | | * current state, but are not, launch them. |
3323 | | */ |
3324 | | static void |
3325 | | LaunchMissingBackgroundProcesses(void) |
3326 | 0 | { |
3327 | | /* Syslogger is active in all states */ |
3328 | 0 | if (SysLoggerPMChild == NULL && Logging_collector) |
3329 | 0 | StartSysLogger(); |
3330 | | |
3331 | | /* |
3332 | | * The number of configured workers might have changed, or a prior start |
3333 | | * of a worker might have failed. Check if we need to start/stop any |
3334 | | * workers. |
3335 | | * |
3336 | | * A config file change will always lead to this function being called, so |
3337 | | * we always will process the config change in a timely manner. |
3338 | | */ |
3339 | 0 | maybe_start_io_workers(); |
3340 | | |
3341 | | /* |
3342 | | * The checkpointer and the background writer are active from the start, |
3343 | | * until shutdown is initiated. |
3344 | | * |
3345 | | * (If the checkpointer is not running when we enter the |
3346 | | * PM_WAIT_XLOG_SHUTDOWN state, it is launched one more time to perform |
3347 | | * the shutdown checkpoint. That's done in PostmasterStateMachine(), not |
3348 | | * here.) |
3349 | | */ |
3350 | 0 | if (pmState == PM_RUN || pmState == PM_RECOVERY || |
3351 | 0 | pmState == PM_HOT_STANDBY || pmState == PM_STARTUP) |
3352 | 0 | { |
3353 | 0 | if (CheckpointerPMChild == NULL) |
3354 | 0 | CheckpointerPMChild = StartChildProcess(B_CHECKPOINTER); |
3355 | 0 | if (BgWriterPMChild == NULL) |
3356 | 0 | BgWriterPMChild = StartChildProcess(B_BG_WRITER); |
3357 | 0 | } |
3358 | | |
3359 | | /* |
3360 | | * WAL writer is needed only in normal operation (else we cannot be |
3361 | | * writing any new WAL). |
3362 | | */ |
3363 | 0 | if (WalWriterPMChild == NULL && pmState == PM_RUN) |
3364 | 0 | WalWriterPMChild = StartChildProcess(B_WAL_WRITER); |
3365 | | |
3366 | | /* |
3367 | | * We don't want autovacuum to run in binary upgrade mode because |
3368 | | * autovacuum might update relfrozenxid for empty tables before the |
3369 | | * physical files are put in place. |
3370 | | */ |
3371 | 0 | if (!IsBinaryUpgrade && AutoVacLauncherPMChild == NULL && |
3372 | 0 | (AutoVacuumingActive() || start_autovac_launcher) && |
3373 | 0 | pmState == PM_RUN) |
3374 | 0 | { |
3375 | 0 | AutoVacLauncherPMChild = StartChildProcess(B_AUTOVAC_LAUNCHER); |
3376 | 0 | if (AutoVacLauncherPMChild != NULL) |
3377 | 0 | start_autovac_launcher = false; /* signal processed */ |
3378 | 0 | } |
3379 | | |
3380 | | /* |
3381 | | * If WAL archiving is enabled always, we are allowed to start archiver |
3382 | | * even during recovery. |
3383 | | */ |
3384 | 0 | if (PgArchPMChild == NULL && |
3385 | 0 | ((XLogArchivingActive() && pmState == PM_RUN) || |
3386 | 0 | (XLogArchivingAlways() && (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && |
3387 | 0 | PgArchCanRestart()) |
3388 | 0 | PgArchPMChild = StartChildProcess(B_ARCHIVER); |
3389 | | |
3390 | | /* |
3391 | | * If we need to start a slot sync worker, try to do that now |
3392 | | * |
3393 | | * We allow to start the slot sync worker when we are on a hot standby, |
3394 | | * fast or immediate shutdown is not in progress, slot sync parameters are |
3395 | | * configured correctly, and it is the first time of worker's launch, or |
3396 | | * enough time has passed since the worker was launched last. |
3397 | | */ |
3398 | 0 | if (SlotSyncWorkerPMChild == NULL && pmState == PM_HOT_STANDBY && |
3399 | 0 | Shutdown <= SmartShutdown && sync_replication_slots && |
3400 | 0 | ValidateSlotSyncParams(LOG) && SlotSyncWorkerCanRestart()) |
3401 | 0 | SlotSyncWorkerPMChild = StartChildProcess(B_SLOTSYNC_WORKER); |
3402 | | |
3403 | | /* |
3404 | | * If we need to start a WAL receiver, try to do that now |
3405 | | * |
3406 | | * Note: if a walreceiver process is already running, it might seem that |
3407 | | * we should clear WalReceiverRequested. However, there's a race |
3408 | | * condition if the walreceiver terminates and the startup process |
3409 | | * immediately requests a new one: it's quite possible to get the signal |
3410 | | * for the request before reaping the dead walreceiver process. Better to |
3411 | | * risk launching an extra walreceiver than to miss launching one we need. |
3412 | | * (The walreceiver code has logic to recognize that it should go away if |
3413 | | * not needed.) |
3414 | | */ |
3415 | 0 | if (WalReceiverRequested) |
3416 | 0 | { |
3417 | 0 | if (WalReceiverPMChild == NULL && |
3418 | 0 | (pmState == PM_STARTUP || pmState == PM_RECOVERY || |
3419 | 0 | pmState == PM_HOT_STANDBY) && |
3420 | 0 | Shutdown <= SmartShutdown) |
3421 | 0 | { |
3422 | 0 | WalReceiverPMChild = StartChildProcess(B_WAL_RECEIVER); |
3423 | 0 | if (WalReceiverPMChild != NULL) |
3424 | 0 | WalReceiverRequested = false; |
3425 | | /* else leave the flag set, so we'll try again later */ |
3426 | 0 | } |
3427 | 0 | } |
3428 | | |
3429 | | /* If we need to start a WAL summarizer, try to do that now */ |
3430 | 0 | if (summarize_wal && WalSummarizerPMChild == NULL && |
3431 | 0 | (pmState == PM_RUN || pmState == PM_HOT_STANDBY) && |
3432 | 0 | Shutdown <= SmartShutdown) |
3433 | 0 | WalSummarizerPMChild = StartChildProcess(B_WAL_SUMMARIZER); |
3434 | | |
3435 | | /* Get other worker processes running, if needed */ |
3436 | 0 | if (StartWorkerNeeded || HaveCrashedWorker) |
3437 | 0 | maybe_start_bgworkers(); |
3438 | 0 | } |
3439 | | |
3440 | | /* |
3441 | | * Return string representation of signal. |
3442 | | * |
3443 | | * Because this is only implemented for signals we already rely on in this |
3444 | | * file we don't need to deal with unimplemented or same-numeric-value signals |
3445 | | * (as we'd e.g. have to for EWOULDBLOCK / EAGAIN). |
3446 | | */ |
3447 | | static const char * |
3448 | | pm_signame(int signal) |
3449 | 0 | { |
3450 | 0 | #define PM_TOSTR_CASE(sym) case sym: return #sym |
3451 | 0 | switch (signal) |
3452 | 0 | { |
3453 | 0 | PM_TOSTR_CASE(SIGABRT); |
3454 | 0 | PM_TOSTR_CASE(SIGCHLD); |
3455 | 0 | PM_TOSTR_CASE(SIGHUP); |
3456 | 0 | PM_TOSTR_CASE(SIGINT); |
3457 | 0 | PM_TOSTR_CASE(SIGKILL); |
3458 | 0 | PM_TOSTR_CASE(SIGQUIT); |
3459 | 0 | PM_TOSTR_CASE(SIGTERM); |
3460 | 0 | PM_TOSTR_CASE(SIGUSR1); |
3461 | 0 | PM_TOSTR_CASE(SIGUSR2); |
3462 | 0 | default: |
3463 | | /* all signals sent by postmaster should be listed here */ |
3464 | 0 | Assert(false); |
3465 | 0 | return "(unknown)"; |
3466 | 0 | } |
3467 | 0 | #undef PM_TOSTR_CASE |
3468 | | |
3469 | 0 | return ""; /* silence compiler */ |
3470 | 0 | } |
3471 | | |
3472 | | /* |
3473 | | * Send a signal to a postmaster child process |
3474 | | * |
3475 | | * On systems that have setsid(), each child process sets itself up as a |
3476 | | * process group leader. For signals that are generally interpreted in the |
3477 | | * appropriate fashion, we signal the entire process group not just the |
3478 | | * direct child process. This allows us to, for example, SIGQUIT a blocked |
3479 | | * archive_recovery script, or SIGINT a script being run by a backend via |
3480 | | * system(). |
3481 | | * |
3482 | | * There is a race condition for recently-forked children: they might not |
3483 | | * have executed setsid() yet. So we signal the child directly as well as |
3484 | | * the group. We assume such a child will handle the signal before trying |
3485 | | * to spawn any grandchild processes. We also assume that signaling the |
3486 | | * child twice will not cause any problems. |
3487 | | */ |
3488 | | static void |
3489 | | signal_child(PMChild *pmchild, int signal) |
3490 | 0 | { |
3491 | 0 | pid_t pid = pmchild->pid; |
3492 | |
|
3493 | 0 | ereport(DEBUG3, |
3494 | 0 | (errmsg_internal("sending signal %d/%s to %s process with pid %d", |
3495 | 0 | signal, pm_signame(signal), |
3496 | 0 | GetBackendTypeDesc(pmchild->bkend_type), |
3497 | 0 | (int) pmchild->pid))); |
3498 | | |
3499 | 0 | if (kill(pid, signal) < 0) |
3500 | 0 | elog(DEBUG3, "kill(%ld,%d) failed: %m", (long) pid, signal); |
3501 | 0 | #ifdef HAVE_SETSID |
3502 | 0 | switch (signal) |
3503 | 0 | { |
3504 | 0 | case SIGINT: |
3505 | 0 | case SIGTERM: |
3506 | 0 | case SIGQUIT: |
3507 | 0 | case SIGKILL: |
3508 | 0 | case SIGABRT: |
3509 | 0 | if (kill(-pid, signal) < 0) |
3510 | 0 | elog(DEBUG3, "kill(%ld,%d) failed: %m", (long) (-pid), signal); |
3511 | 0 | break; |
3512 | 0 | default: |
3513 | 0 | break; |
3514 | 0 | } |
3515 | 0 | #endif |
3516 | 0 | } |
3517 | | |
3518 | | /* |
3519 | | * Send a signal to the targeted children. |
3520 | | */ |
3521 | | static bool |
3522 | | SignalChildren(int signal, BackendTypeMask targetMask) |
3523 | 0 | { |
3524 | 0 | dlist_iter iter; |
3525 | 0 | bool signaled = false; |
3526 | |
|
3527 | 0 | dlist_foreach(iter, &ActiveChildList) |
3528 | 0 | { |
3529 | 0 | PMChild *bp = dlist_container(PMChild, elem, iter.cur); |
3530 | | |
3531 | | /* |
3532 | | * If we need to distinguish between B_BACKEND and B_WAL_SENDER, check |
3533 | | * if any B_BACKEND backends have recently announced that they are |
3534 | | * actually WAL senders. |
3535 | | */ |
3536 | 0 | if (btmask_contains(targetMask, B_WAL_SENDER) != btmask_contains(targetMask, B_BACKEND) && |
3537 | 0 | bp->bkend_type == B_BACKEND) |
3538 | 0 | { |
3539 | 0 | if (IsPostmasterChildWalSender(bp->child_slot)) |
3540 | 0 | bp->bkend_type = B_WAL_SENDER; |
3541 | 0 | } |
3542 | |
|
3543 | 0 | if (!btmask_contains(targetMask, bp->bkend_type)) |
3544 | 0 | continue; |
3545 | | |
3546 | 0 | signal_child(bp, signal); |
3547 | 0 | signaled = true; |
3548 | 0 | } |
3549 | 0 | return signaled; |
3550 | 0 | } |
3551 | | |
3552 | | /* |
3553 | | * Send a termination signal to children. This considers all of our children |
3554 | | * processes, except syslogger. |
3555 | | */ |
3556 | | static void |
3557 | | TerminateChildren(int signal) |
3558 | 0 | { |
3559 | 0 | SignalChildren(signal, btmask_all_except(B_LOGGER)); |
3560 | 0 | if (StartupPMChild != NULL) |
3561 | 0 | { |
3562 | 0 | if (signal == SIGQUIT || signal == SIGKILL || signal == SIGABRT) |
3563 | 0 | StartupStatus = STARTUP_SIGNALED; |
3564 | 0 | } |
3565 | 0 | } |
3566 | | |
3567 | | /* |
3568 | | * BackendStartup -- start backend process |
3569 | | * |
3570 | | * returns: STATUS_ERROR if the fork failed, STATUS_OK otherwise. |
3571 | | * |
3572 | | * Note: if you change this code, also consider StartAutovacuumWorker and |
3573 | | * StartBackgroundWorker. |
3574 | | */ |
3575 | | static int |
3576 | | BackendStartup(ClientSocket *client_sock) |
3577 | | { |
3578 | | PMChild *bn = NULL; |
3579 | | pid_t pid; |
3580 | | BackendStartupData startup_data; |
3581 | | CAC_state cac; |
3582 | | |
3583 | | /* |
3584 | | * Capture time that Postmaster got a socket from accept (for logging |
3585 | | * connection establishment and setup total duration). |
3586 | | */ |
3587 | | startup_data.socket_created = GetCurrentTimestamp(); |
3588 | | |
3589 | | /* |
3590 | | * Allocate and assign the child slot. Note we must do this before |
3591 | | * forking, so that we can handle failures (out of memory or child-process |
3592 | | * slots) cleanly. |
3593 | | */ |
3594 | | cac = canAcceptConnections(B_BACKEND); |
3595 | | if (cac == CAC_OK) |
3596 | | { |
3597 | | /* Can change later to B_WAL_SENDER */ |
3598 | | bn = AssignPostmasterChildSlot(B_BACKEND); |
3599 | | if (!bn) |
3600 | | { |
3601 | | /* |
3602 | | * Too many regular child processes; launch a dead-end child |
3603 | | * process instead. |
3604 | | */ |
3605 | | cac = CAC_TOOMANY; |
3606 | | } |
3607 | | } |
3608 | | if (!bn) |
3609 | | { |
3610 | | bn = AllocDeadEndChild(); |
3611 | | if (!bn) |
3612 | | { |
3613 | | ereport(LOG, |
3614 | | (errcode(ERRCODE_OUT_OF_MEMORY), |
3615 | | errmsg("out of memory"))); |
3616 | | return STATUS_ERROR; |
3617 | | } |
3618 | | } |
3619 | | |
3620 | | /* Pass down canAcceptConnections state */ |
3621 | | startup_data.canAcceptConnections = cac; |
3622 | | bn->rw = NULL; |
3623 | | |
3624 | | /* Hasn't asked to be notified about any bgworkers yet */ |
3625 | | bn->bgworker_notify = false; |
3626 | | |
3627 | | pid = postmaster_child_launch(bn->bkend_type, bn->child_slot, |
3628 | | &startup_data, sizeof(startup_data), |
3629 | | client_sock); |
3630 | | if (pid < 0) |
3631 | | { |
3632 | | /* in parent, fork failed */ |
3633 | | int save_errno = errno; |
3634 | | |
3635 | | (void) ReleasePostmasterChildSlot(bn); |
3636 | | errno = save_errno; |
3637 | | ereport(LOG, |
3638 | | (errmsg("could not fork new process for connection: %m"))); |
3639 | | report_fork_failure_to_client(client_sock, save_errno); |
3640 | | return STATUS_ERROR; |
3641 | | } |
3642 | | |
3643 | | /* in parent, successful fork */ |
3644 | | ereport(DEBUG2, |
3645 | | (errmsg_internal("forked new %s, pid=%d socket=%d", |
3646 | | GetBackendTypeDesc(bn->bkend_type), |
3647 | | (int) pid, (int) client_sock->sock))); |
3648 | | |
3649 | | /* |
3650 | | * Everything's been successful, it's safe to add this backend to our list |
3651 | | * of backends. |
3652 | | */ |
3653 | | bn->pid = pid; |
3654 | | return STATUS_OK; |
3655 | | } |
3656 | | |
3657 | | /* |
3658 | | * Try to report backend fork() failure to client before we close the |
3659 | | * connection. Since we do not care to risk blocking the postmaster on |
3660 | | * this connection, we set the connection to non-blocking and try only once. |
3661 | | * |
3662 | | * This is grungy special-purpose code; we cannot use backend libpq since |
3663 | | * it's not up and running. |
3664 | | */ |
3665 | | static void |
3666 | | report_fork_failure_to_client(ClientSocket *client_sock, int errnum) |
3667 | 0 | { |
3668 | 0 | char buffer[1000]; |
3669 | 0 | int rc; |
3670 | | |
3671 | | /* Format the error message packet (always V2 protocol) */ |
3672 | 0 | snprintf(buffer, sizeof(buffer), "E%s%s\n", |
3673 | 0 | _("could not fork new process for connection: "), |
3674 | 0 | strerror(errnum)); |
3675 | | |
3676 | | /* Set port to non-blocking. Don't do send() if this fails */ |
3677 | 0 | if (!pg_set_noblock(client_sock->sock)) |
3678 | 0 | return; |
3679 | | |
3680 | | /* We'll retry after EINTR, but ignore all other failures */ |
3681 | 0 | do |
3682 | 0 | { |
3683 | 0 | rc = send(client_sock->sock, buffer, strlen(buffer) + 1, 0); |
3684 | 0 | } while (rc < 0 && errno == EINTR); |
3685 | 0 | } |
3686 | | |
3687 | | /* |
3688 | | * ExitPostmaster -- cleanup |
3689 | | * |
3690 | | * Do NOT call exit() directly --- always go through here! |
3691 | | */ |
3692 | | static void |
3693 | | ExitPostmaster(int status) |
3694 | 0 | { |
3695 | | #ifdef HAVE_PTHREAD_IS_THREADED_NP |
3696 | | |
3697 | | /* |
3698 | | * There is no known cause for a postmaster to become multithreaded after |
3699 | | * startup. However, we might reach here via an error exit before |
3700 | | * reaching the test in PostmasterMain, so provide the same hint as there. |
3701 | | * This message uses LOG level, because an unclean shutdown at this point |
3702 | | * would usually not look much different from a clean shutdown. |
3703 | | */ |
3704 | | if (pthread_is_threaded_np() != 0) |
3705 | | ereport(LOG, |
3706 | | (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), |
3707 | | errmsg("postmaster became multithreaded"), |
3708 | | errhint("Set the LC_ALL environment variable to a valid locale."))); |
3709 | | #endif |
3710 | | |
3711 | | /* should cleanup shared memory and kill all backends */ |
3712 | | |
3713 | | /* |
3714 | | * Not sure of the semantics here. When the Postmaster dies, should the |
3715 | | * backends all be killed? probably not. |
3716 | | * |
3717 | | * MUST -- vadim 05-10-1999 |
3718 | | */ |
3719 | |
|
3720 | 0 | proc_exit(status); |
3721 | 0 | } |
3722 | | |
3723 | | /* |
3724 | | * Handle pmsignal conditions representing requests from backends, |
3725 | | * and check for promote and logrotate requests from pg_ctl. |
3726 | | */ |
3727 | | static void |
3728 | | process_pm_pmsignal(void) |
3729 | 0 | { |
3730 | 0 | bool request_state_update = false; |
3731 | |
|
3732 | 0 | pending_pm_pmsignal = false; |
3733 | |
|
3734 | 0 | ereport(DEBUG2, |
3735 | 0 | (errmsg_internal("postmaster received pmsignal signal"))); |
3736 | | |
3737 | | /* |
3738 | | * RECOVERY_STARTED and BEGIN_HOT_STANDBY signals are ignored in |
3739 | | * unexpected states. If the startup process quickly starts up, completes |
3740 | | * recovery, exits, we might process the death of the startup process |
3741 | | * first. We don't want to go back to recovery in that case. |
3742 | | */ |
3743 | 0 | if (CheckPostmasterSignal(PMSIGNAL_RECOVERY_STARTED) && |
3744 | 0 | pmState == PM_STARTUP && Shutdown == NoShutdown) |
3745 | 0 | { |
3746 | | /* WAL redo has started. We're out of reinitialization. */ |
3747 | 0 | FatalError = false; |
3748 | 0 | AbortStartTime = 0; |
3749 | 0 | reachedConsistency = false; |
3750 | | |
3751 | | /* |
3752 | | * Start the archiver if we're responsible for (re-)archiving received |
3753 | | * files. |
3754 | | */ |
3755 | 0 | Assert(PgArchPMChild == NULL); |
3756 | 0 | if (XLogArchivingAlways()) |
3757 | 0 | PgArchPMChild = StartChildProcess(B_ARCHIVER); |
3758 | | |
3759 | | /* |
3760 | | * If we aren't planning to enter hot standby mode later, treat |
3761 | | * RECOVERY_STARTED as meaning we're out of startup, and report status |
3762 | | * accordingly. |
3763 | | */ |
3764 | 0 | if (!EnableHotStandby) |
3765 | 0 | { |
3766 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STANDBY); |
3767 | | #ifdef USE_SYSTEMD |
3768 | | sd_notify(0, "READY=1"); |
3769 | | #endif |
3770 | 0 | } |
3771 | |
|
3772 | 0 | UpdatePMState(PM_RECOVERY); |
3773 | 0 | } |
3774 | |
|
3775 | 0 | if (CheckPostmasterSignal(PMSIGNAL_RECOVERY_CONSISTENT) && |
3776 | 0 | pmState == PM_RECOVERY && Shutdown == NoShutdown) |
3777 | 0 | { |
3778 | 0 | reachedConsistency = true; |
3779 | 0 | } |
3780 | |
|
3781 | 0 | if (CheckPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY) && |
3782 | 0 | (pmState == PM_RECOVERY && Shutdown == NoShutdown)) |
3783 | 0 | { |
3784 | 0 | ereport(LOG, |
3785 | 0 | (errmsg("database system is ready to accept read-only connections"))); |
3786 | | |
3787 | | /* Report status */ |
3788 | 0 | AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_READY); |
3789 | | #ifdef USE_SYSTEMD |
3790 | | sd_notify(0, "READY=1"); |
3791 | | #endif |
3792 | |
|
3793 | 0 | UpdatePMState(PM_HOT_STANDBY); |
3794 | 0 | connsAllowed = true; |
3795 | | |
3796 | | /* Some workers may be scheduled to start now */ |
3797 | 0 | StartWorkerNeeded = true; |
3798 | 0 | } |
3799 | | |
3800 | | /* Process IO worker start requests. */ |
3801 | 0 | if (CheckPostmasterSignal(PMSIGNAL_IO_WORKER_GROW)) |
3802 | 0 | { |
3803 | | /* |
3804 | | * No local flag, as the state is exposed through pgaio_worker_*() |
3805 | | * functions. This signal is received on potentially actionable level |
3806 | | * changes, so that maybe_start_io_workers() will run. |
3807 | | */ |
3808 | 0 | } |
3809 | | |
3810 | | /* Process background worker state changes. */ |
3811 | 0 | if (CheckPostmasterSignal(PMSIGNAL_BACKGROUND_WORKER_CHANGE)) |
3812 | 0 | { |
3813 | | /* Accept new worker requests only if not stopping. */ |
3814 | 0 | BackgroundWorkerStateChange(pmState < PM_STOP_BACKENDS); |
3815 | 0 | StartWorkerNeeded = true; |
3816 | 0 | } |
3817 | | |
3818 | | /* Tell syslogger to rotate logfile if requested */ |
3819 | 0 | if (SysLoggerPMChild != NULL) |
3820 | 0 | { |
3821 | 0 | if (CheckLogrotateSignal()) |
3822 | 0 | { |
3823 | 0 | signal_child(SysLoggerPMChild, SIGUSR1); |
3824 | 0 | RemoveLogrotateSignalFiles(); |
3825 | 0 | } |
3826 | 0 | else if (CheckPostmasterSignal(PMSIGNAL_ROTATE_LOGFILE)) |
3827 | 0 | { |
3828 | 0 | signal_child(SysLoggerPMChild, SIGUSR1); |
3829 | 0 | } |
3830 | 0 | } |
3831 | |
|
3832 | 0 | if (CheckPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER) && |
3833 | 0 | Shutdown <= SmartShutdown && pmState < PM_STOP_BACKENDS) |
3834 | 0 | { |
3835 | | /* |
3836 | | * Start one iteration of the autovacuum daemon, even if autovacuuming |
3837 | | * is nominally not enabled. This is so we can have an active defense |
3838 | | * against transaction ID wraparound. We set a flag for the main loop |
3839 | | * to do it rather than trying to do it here --- this is because the |
3840 | | * autovac process itself may send the signal, and we want to handle |
3841 | | * that by launching another iteration as soon as the current one |
3842 | | * completes. |
3843 | | */ |
3844 | 0 | start_autovac_launcher = true; |
3845 | 0 | } |
3846 | |
|
3847 | 0 | if (CheckPostmasterSignal(PMSIGNAL_START_AUTOVAC_WORKER) && |
3848 | 0 | Shutdown <= SmartShutdown && pmState < PM_STOP_BACKENDS) |
3849 | 0 | { |
3850 | | /* The autovacuum launcher wants us to start a worker process. */ |
3851 | 0 | StartAutovacuumWorker(); |
3852 | 0 | } |
3853 | |
|
3854 | 0 | if (CheckPostmasterSignal(PMSIGNAL_START_WALRECEIVER)) |
3855 | 0 | { |
3856 | | /* Startup Process wants us to start the walreceiver process. */ |
3857 | 0 | WalReceiverRequested = true; |
3858 | 0 | } |
3859 | |
|
3860 | 0 | if (CheckPostmasterSignal(PMSIGNAL_XLOG_IS_SHUTDOWN)) |
3861 | 0 | { |
3862 | | /* Checkpointer completed the shutdown checkpoint */ |
3863 | 0 | if (pmState == PM_WAIT_XLOG_SHUTDOWN) |
3864 | 0 | { |
3865 | | /* |
3866 | | * If we have an archiver subprocess, tell it to do a last archive |
3867 | | * cycle and quit. Likewise, if we have walsender processes, tell |
3868 | | * them to send any remaining WAL and quit. |
3869 | | */ |
3870 | 0 | Assert(Shutdown > NoShutdown); |
3871 | | |
3872 | | /* Waken archiver for the last time */ |
3873 | 0 | if (PgArchPMChild != NULL) |
3874 | 0 | signal_child(PgArchPMChild, SIGUSR2); |
3875 | | |
3876 | | /* |
3877 | | * Waken walsenders for the last time. No regular backends should |
3878 | | * be around anymore. |
3879 | | */ |
3880 | 0 | SignalChildren(SIGUSR2, btmask(B_WAL_SENDER)); |
3881 | |
|
3882 | 0 | UpdatePMState(PM_WAIT_XLOG_ARCHIVAL); |
3883 | 0 | } |
3884 | 0 | else if (!FatalError && Shutdown != ImmediateShutdown) |
3885 | 0 | { |
3886 | | /* |
3887 | | * Checkpointer only ought to perform the shutdown checkpoint |
3888 | | * during shutdown. If somehow checkpointer did so in another |
3889 | | * situation, we have no choice but to crash-restart. |
3890 | | * |
3891 | | * It's possible however that we get PMSIGNAL_XLOG_IS_SHUTDOWN |
3892 | | * outside of PM_WAIT_XLOG_SHUTDOWN if an orderly shutdown was |
3893 | | * "interrupted" by a crash or an immediate shutdown. |
3894 | | */ |
3895 | 0 | ereport(LOG, |
3896 | 0 | (errmsg("WAL was shut down unexpectedly"))); |
3897 | | |
3898 | | /* |
3899 | | * Doesn't seem likely to help to take send_abort_for_crash into |
3900 | | * account here. |
3901 | | */ |
3902 | 0 | HandleFatalError(PMQUIT_FOR_CRASH, false); |
3903 | 0 | } |
3904 | | |
3905 | | /* |
3906 | | * Need to run PostmasterStateMachine() to check if we already can go |
3907 | | * to the next state. |
3908 | | */ |
3909 | 0 | request_state_update = true; |
3910 | 0 | } |
3911 | | |
3912 | | /* |
3913 | | * Try to advance postmaster's state machine, if a child requests it. |
3914 | | */ |
3915 | 0 | if (CheckPostmasterSignal(PMSIGNAL_ADVANCE_STATE_MACHINE)) |
3916 | 0 | { |
3917 | 0 | request_state_update = true; |
3918 | 0 | } |
3919 | | |
3920 | | /* |
3921 | | * Be careful about the order of this action relative to this function's |
3922 | | * other actions. Generally, this should be after other actions, in case |
3923 | | * they have effects PostmasterStateMachine would need to know about. |
3924 | | * However, we should do it before the CheckPromoteSignal step, which |
3925 | | * cannot have any (immediate) effect on the state machine, but does |
3926 | | * depend on what state we're in now. |
3927 | | */ |
3928 | 0 | if (request_state_update) |
3929 | 0 | { |
3930 | 0 | PostmasterStateMachine(); |
3931 | 0 | } |
3932 | |
|
3933 | 0 | if (StartupPMChild != NULL && |
3934 | 0 | (pmState == PM_STARTUP || pmState == PM_RECOVERY || |
3935 | 0 | pmState == PM_HOT_STANDBY) && |
3936 | 0 | CheckPromoteSignal()) |
3937 | 0 | { |
3938 | | /* |
3939 | | * Tell startup process to finish recovery. |
3940 | | * |
3941 | | * Leave the promote signal file in place and let the Startup process |
3942 | | * do the unlink. |
3943 | | */ |
3944 | 0 | signal_child(StartupPMChild, SIGUSR2); |
3945 | 0 | } |
3946 | 0 | } |
3947 | | |
3948 | | /* |
3949 | | * Dummy signal handler |
3950 | | * |
3951 | | * We use this for signals that we don't actually use in the postmaster, |
3952 | | * but we do use in backends. If we were to PG_SIG_IGN such signals in the |
3953 | | * postmaster, then a newly started backend might drop a signal that arrives |
3954 | | * before it's able to reconfigure its signal processing. (See notes in |
3955 | | * tcop/postgres.c.) |
3956 | | */ |
3957 | | static void |
3958 | | dummy_handler(SIGNAL_ARGS) |
3959 | 0 | { |
3960 | 0 | } |
3961 | | |
3962 | | /* |
3963 | | * Count up number of child processes of specified types. |
3964 | | */ |
3965 | | static int |
3966 | | CountChildren(BackendTypeMask targetMask) |
3967 | | { |
3968 | | dlist_iter iter; |
3969 | | int cnt = 0; |
3970 | | |
3971 | | dlist_foreach(iter, &ActiveChildList) |
3972 | | { |
3973 | | PMChild *bp = dlist_container(PMChild, elem, iter.cur); |
3974 | | |
3975 | | /* |
3976 | | * If we need to distinguish between B_BACKEND and B_WAL_SENDER, check |
3977 | | * if any B_BACKEND backends have recently announced that they are |
3978 | | * actually WAL senders. |
3979 | | */ |
3980 | | if (btmask_contains(targetMask, B_WAL_SENDER) != btmask_contains(targetMask, B_BACKEND) && |
3981 | | bp->bkend_type == B_BACKEND) |
3982 | | { |
3983 | | if (IsPostmasterChildWalSender(bp->child_slot)) |
3984 | | bp->bkend_type = B_WAL_SENDER; |
3985 | | } |
3986 | | |
3987 | | if (!btmask_contains(targetMask, bp->bkend_type)) |
3988 | | continue; |
3989 | | |
3990 | | ereport(DEBUG4, |
3991 | | (errmsg_internal("%s process %d is still running", |
3992 | | GetBackendTypeDesc(bp->bkend_type), (int) bp->pid))); |
3993 | | |
3994 | | cnt++; |
3995 | | } |
3996 | | return cnt; |
3997 | | } |
3998 | | |
3999 | | |
4000 | | /* |
4001 | | * StartChildProcess -- start an auxiliary process for the postmaster |
4002 | | * |
4003 | | * "type" determines what kind of child will be started. All child types |
4004 | | * initially go to AuxiliaryProcessMain, which will handle common setup. |
4005 | | * |
4006 | | * Return value of StartChildProcess is subprocess' PMChild entry, or NULL on |
4007 | | * failure. |
4008 | | */ |
4009 | | static PMChild * |
4010 | | StartChildProcess(BackendType type) |
4011 | 0 | { |
4012 | 0 | PMChild *pmchild; |
4013 | 0 | pid_t pid; |
4014 | |
|
4015 | 0 | pmchild = AssignPostmasterChildSlot(type); |
4016 | 0 | if (!pmchild) |
4017 | 0 | { |
4018 | 0 | if (type == B_AUTOVAC_WORKER) |
4019 | 0 | ereport(LOG, |
4020 | 0 | (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), |
4021 | 0 | errmsg("no slot available for new autovacuum worker process"))); |
4022 | 0 | else |
4023 | 0 | { |
4024 | | /* shouldn't happen because we allocate enough slots */ |
4025 | 0 | elog(LOG, "no postmaster child slot available for aux process"); |
4026 | 0 | } |
4027 | 0 | return NULL; |
4028 | 0 | } |
4029 | | |
4030 | 0 | pid = postmaster_child_launch(type, pmchild->child_slot, NULL, 0, NULL); |
4031 | 0 | if (pid < 0) |
4032 | 0 | { |
4033 | | /* in parent, fork failed */ |
4034 | 0 | ReleasePostmasterChildSlot(pmchild); |
4035 | 0 | ereport(LOG, |
4036 | 0 | (errmsg("could not fork \"%s\" process: %m", PostmasterChildName(type)))); |
4037 | | |
4038 | | /* |
4039 | | * fork failure is fatal during startup, but there's no need to choke |
4040 | | * immediately if starting other child types fails. |
4041 | | */ |
4042 | 0 | if (type == B_STARTUP) |
4043 | 0 | ExitPostmaster(1); |
4044 | 0 | return NULL; |
4045 | 0 | } |
4046 | | |
4047 | | /* in parent, successful fork */ |
4048 | 0 | pmchild->pid = pid; |
4049 | 0 | return pmchild; |
4050 | 0 | } |
4051 | | |
4052 | | /* |
4053 | | * StartSysLogger -- start the syslogger process |
4054 | | */ |
4055 | | void |
4056 | | StartSysLogger(void) |
4057 | 0 | { |
4058 | 0 | Assert(SysLoggerPMChild == NULL); |
4059 | |
|
4060 | 0 | SysLoggerPMChild = AssignPostmasterChildSlot(B_LOGGER); |
4061 | 0 | if (!SysLoggerPMChild) |
4062 | 0 | elog(PANIC, "no postmaster child slot available for syslogger"); |
4063 | 0 | SysLoggerPMChild->pid = SysLogger_Start(SysLoggerPMChild->child_slot); |
4064 | 0 | if (SysLoggerPMChild->pid == 0) |
4065 | 0 | { |
4066 | 0 | ReleasePostmasterChildSlot(SysLoggerPMChild); |
4067 | 0 | SysLoggerPMChild = NULL; |
4068 | 0 | } |
4069 | 0 | } |
4070 | | |
4071 | | /* |
4072 | | * StartAutovacuumWorker |
4073 | | * Start an autovac worker process. |
4074 | | * |
4075 | | * This function is here because it enters the resulting PID into the |
4076 | | * postmaster's private backends list. |
4077 | | * |
4078 | | * NB -- this code very roughly matches BackendStartup. |
4079 | | */ |
4080 | | static void |
4081 | | StartAutovacuumWorker(void) |
4082 | 0 | { |
4083 | 0 | PMChild *bn; |
4084 | | |
4085 | | /* |
4086 | | * If not in condition to run a process, don't try, but handle it like a |
4087 | | * fork failure. This does not normally happen, since the signal is only |
4088 | | * supposed to be sent by autovacuum launcher when it's OK to do it, but |
4089 | | * we have to check to avoid race-condition problems during DB state |
4090 | | * changes. |
4091 | | */ |
4092 | 0 | if (canAcceptConnections(B_AUTOVAC_WORKER) == CAC_OK) |
4093 | 0 | { |
4094 | 0 | bn = StartChildProcess(B_AUTOVAC_WORKER); |
4095 | 0 | if (bn) |
4096 | 0 | { |
4097 | 0 | bn->bgworker_notify = false; |
4098 | 0 | bn->rw = NULL; |
4099 | 0 | return; |
4100 | 0 | } |
4101 | 0 | else |
4102 | 0 | { |
4103 | | /* |
4104 | | * fork failed, fall through to report -- actual error message was |
4105 | | * logged by StartChildProcess |
4106 | | */ |
4107 | 0 | } |
4108 | 0 | } |
4109 | | |
4110 | | /* |
4111 | | * Report the failure to the launcher, if it's running. (If it's not, we |
4112 | | * might not even be connected to shared memory, so don't try to call |
4113 | | * AutoVacWorkerFailed.) Note that we also need to signal it so that it |
4114 | | * responds to the condition, but we don't do that here, instead waiting |
4115 | | * for ServerLoop to do it. This way we avoid a ping-pong signaling in |
4116 | | * quick succession between the autovac launcher and postmaster in case |
4117 | | * things get ugly. |
4118 | | */ |
4119 | 0 | if (AutoVacLauncherPMChild != NULL) |
4120 | 0 | { |
4121 | 0 | AutoVacWorkerFailed(); |
4122 | 0 | avlauncher_needs_signal = true; |
4123 | 0 | } |
4124 | 0 | } |
4125 | | |
4126 | | |
4127 | | /* |
4128 | | * Create the opts file |
4129 | | */ |
4130 | | static bool |
4131 | | CreateOptsFile(int argc, char *argv[], char *fullprogname) |
4132 | | { |
4133 | | FILE *fp; |
4134 | | int i; |
4135 | | |
4136 | | #define OPTS_FILE "postmaster.opts" |
4137 | | |
4138 | | if ((fp = fopen(OPTS_FILE, "w")) == NULL) |
4139 | | { |
4140 | | ereport(LOG, |
4141 | | (errcode_for_file_access(), |
4142 | | errmsg("could not create file \"%s\": %m", OPTS_FILE))); |
4143 | | return false; |
4144 | | } |
4145 | | |
4146 | | fprintf(fp, "%s", fullprogname); |
4147 | | for (i = 1; i < argc; i++) |
4148 | | fprintf(fp, " \"%s\"", argv[i]); |
4149 | | fputs("\n", fp); |
4150 | | |
4151 | | if (fclose(fp)) |
4152 | | { |
4153 | | ereport(LOG, |
4154 | | (errcode_for_file_access(), |
4155 | | errmsg("could not write file \"%s\": %m", OPTS_FILE))); |
4156 | | return false; |
4157 | | } |
4158 | | |
4159 | | return true; |
4160 | | } |
4161 | | |
4162 | | |
4163 | | /* |
4164 | | * Start a new bgworker. |
4165 | | * Starting time conditions must have been checked already. |
4166 | | * |
4167 | | * Returns true on success, false on failure. |
4168 | | * In either case, update the RegisteredBgWorker's state appropriately. |
4169 | | * |
4170 | | * NB -- this code very roughly matches BackendStartup. |
4171 | | */ |
4172 | | static bool |
4173 | | StartBackgroundWorker(RegisteredBgWorker *rw) |
4174 | | { |
4175 | | PMChild *bn; |
4176 | | pid_t worker_pid; |
4177 | | |
4178 | | Assert(rw->rw_pid == 0); |
4179 | | |
4180 | | /* |
4181 | | * Allocate and assign the child slot. Note we must do this before |
4182 | | * forking, so that we can handle failures (out of memory or child-process |
4183 | | * slots) cleanly. |
4184 | | * |
4185 | | * Treat failure as though the worker had crashed. That way, the |
4186 | | * postmaster will wait a bit before attempting to start it again; if we |
4187 | | * tried again right away, most likely we'd find ourselves hitting the |
4188 | | * same resource-exhaustion condition. |
4189 | | */ |
4190 | | bn = AssignPostmasterChildSlot(B_BG_WORKER); |
4191 | | if (bn == NULL) |
4192 | | { |
4193 | | ereport(LOG, |
4194 | | (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), |
4195 | | errmsg("no slot available for new background worker process"))); |
4196 | | rw->rw_crashed_at = GetCurrentTimestamp(); |
4197 | | return false; |
4198 | | } |
4199 | | bn->rw = rw; |
4200 | | bn->bkend_type = B_BG_WORKER; |
4201 | | bn->bgworker_notify = false; |
4202 | | |
4203 | | ereport(DEBUG1, |
4204 | | (errmsg_internal("starting background worker process \"%s\"", |
4205 | | rw->rw_worker.bgw_name))); |
4206 | | |
4207 | | worker_pid = postmaster_child_launch(B_BG_WORKER, bn->child_slot, |
4208 | | &rw->rw_worker, sizeof(BackgroundWorker), NULL); |
4209 | | if (worker_pid == -1) |
4210 | | { |
4211 | | /* in postmaster, fork failed ... */ |
4212 | | ereport(LOG, |
4213 | | (errmsg("could not fork background worker process: %m"))); |
4214 | | /* undo what AssignPostmasterChildSlot did */ |
4215 | | ReleasePostmasterChildSlot(bn); |
4216 | | |
4217 | | /* mark entry as crashed, so we'll try again later */ |
4218 | | rw->rw_crashed_at = GetCurrentTimestamp(); |
4219 | | return false; |
4220 | | } |
4221 | | |
4222 | | /* in postmaster, fork successful ... */ |
4223 | | rw->rw_pid = worker_pid; |
4224 | | bn->pid = rw->rw_pid; |
4225 | | ReportBackgroundWorkerPID(rw); |
4226 | | return true; |
4227 | | } |
4228 | | |
4229 | | /* |
4230 | | * Does the current postmaster state require starting a worker with the |
4231 | | * specified start_time? |
4232 | | */ |
4233 | | static bool |
4234 | | bgworker_should_start_now(BgWorkerStartTime start_time) |
4235 | 0 | { |
4236 | 0 | switch (pmState) |
4237 | 0 | { |
4238 | 0 | case PM_NO_CHILDREN: |
4239 | 0 | case PM_WAIT_CHECKPOINTER: |
4240 | 0 | case PM_WAIT_DEAD_END: |
4241 | 0 | case PM_WAIT_XLOG_ARCHIVAL: |
4242 | 0 | case PM_WAIT_XLOG_SHUTDOWN: |
4243 | 0 | case PM_WAIT_IO_WORKERS: |
4244 | 0 | case PM_WAIT_BACKENDS: |
4245 | 0 | case PM_STOP_BACKENDS: |
4246 | 0 | break; |
4247 | | |
4248 | 0 | case PM_RUN: |
4249 | 0 | if (start_time == BgWorkerStart_RecoveryFinished) |
4250 | 0 | return true; |
4251 | 0 | pg_fallthrough; |
4252 | |
|
4253 | 0 | case PM_HOT_STANDBY: |
4254 | 0 | if (start_time == BgWorkerStart_ConsistentState) |
4255 | 0 | return true; |
4256 | 0 | pg_fallthrough; |
4257 | |
|
4258 | 0 | case PM_RECOVERY: |
4259 | 0 | case PM_STARTUP: |
4260 | 0 | case PM_INIT: |
4261 | 0 | if (start_time == BgWorkerStart_PostmasterStart) |
4262 | 0 | return true; |
4263 | 0 | } |
4264 | | |
4265 | 0 | return false; |
4266 | 0 | } |
4267 | | |
4268 | | /* |
4269 | | * If the time is right, start background worker(s). |
4270 | | * |
4271 | | * As a side effect, the bgworker control variables are set or reset |
4272 | | * depending on whether more workers may need to be started. |
4273 | | * |
4274 | | * We limit the number of workers started per call, to avoid consuming the |
4275 | | * postmaster's attention for too long when many such requests are pending. |
4276 | | * As long as StartWorkerNeeded is true, ServerLoop will not block and will |
4277 | | * call this function again after dealing with any other issues. |
4278 | | */ |
4279 | | static void |
4280 | | maybe_start_bgworkers(void) |
4281 | 0 | { |
4282 | 0 | #define MAX_BGWORKERS_TO_LAUNCH 100 |
4283 | 0 | int num_launched = 0; |
4284 | 0 | TimestampTz now = 0; |
4285 | 0 | dlist_mutable_iter iter; |
4286 | | |
4287 | | /* |
4288 | | * During crash recovery, we have no need to be called until the state |
4289 | | * transition out of recovery. |
4290 | | */ |
4291 | 0 | if (FatalError) |
4292 | 0 | { |
4293 | 0 | StartWorkerNeeded = false; |
4294 | 0 | HaveCrashedWorker = false; |
4295 | 0 | return; |
4296 | 0 | } |
4297 | | |
4298 | | /* Don't need to be called again unless we find a reason for it below */ |
4299 | 0 | StartWorkerNeeded = false; |
4300 | 0 | HaveCrashedWorker = false; |
4301 | |
|
4302 | 0 | dlist_foreach_modify(iter, &BackgroundWorkerList) |
4303 | 0 | { |
4304 | 0 | RegisteredBgWorker *rw; |
4305 | |
|
4306 | 0 | rw = dlist_container(RegisteredBgWorker, rw_lnode, iter.cur); |
4307 | | |
4308 | | /* ignore if already running */ |
4309 | 0 | if (rw->rw_pid != 0) |
4310 | 0 | continue; |
4311 | | |
4312 | | /* if marked for death, clean up and remove from list */ |
4313 | 0 | if (rw->rw_terminate) |
4314 | 0 | { |
4315 | 0 | ForgetBackgroundWorker(rw); |
4316 | 0 | continue; |
4317 | 0 | } |
4318 | | |
4319 | | /* |
4320 | | * If this worker has crashed previously, maybe it needs to be |
4321 | | * restarted (unless on registration it specified it doesn't want to |
4322 | | * be restarted at all). Check how long ago did a crash last happen. |
4323 | | * If the last crash is too recent, don't start it right away; let it |
4324 | | * be restarted once enough time has passed. |
4325 | | */ |
4326 | 0 | if (rw->rw_crashed_at != 0) |
4327 | 0 | { |
4328 | 0 | if (rw->rw_worker.bgw_restart_time == BGW_NEVER_RESTART) |
4329 | 0 | { |
4330 | 0 | int notify_pid; |
4331 | |
|
4332 | 0 | notify_pid = rw->rw_worker.bgw_notify_pid; |
4333 | |
|
4334 | 0 | ForgetBackgroundWorker(rw); |
4335 | | |
4336 | | /* Report worker is gone now. */ |
4337 | 0 | if (notify_pid != 0) |
4338 | 0 | kill(notify_pid, SIGUSR1); |
4339 | |
|
4340 | 0 | continue; |
4341 | 0 | } |
4342 | | |
4343 | | /* read system time only when needed */ |
4344 | 0 | if (now == 0) |
4345 | 0 | now = GetCurrentTimestamp(); |
4346 | |
|
4347 | 0 | if (!TimestampDifferenceExceeds(rw->rw_crashed_at, now, |
4348 | 0 | rw->rw_worker.bgw_restart_time * 1000)) |
4349 | 0 | { |
4350 | | /* Set flag to remember that we have workers to start later */ |
4351 | 0 | HaveCrashedWorker = true; |
4352 | 0 | continue; |
4353 | 0 | } |
4354 | 0 | } |
4355 | | |
4356 | 0 | if (bgworker_should_start_now(rw->rw_worker.bgw_start_time)) |
4357 | 0 | { |
4358 | | /* reset crash time before trying to start worker */ |
4359 | 0 | rw->rw_crashed_at = 0; |
4360 | | |
4361 | | /* |
4362 | | * Try to start the worker. |
4363 | | * |
4364 | | * On failure, give up processing workers for now, but set |
4365 | | * StartWorkerNeeded so we'll come back here on the next iteration |
4366 | | * of ServerLoop to try again. (We don't want to wait, because |
4367 | | * there might be additional ready-to-run workers.) We could set |
4368 | | * HaveCrashedWorker as well, since this worker is now marked |
4369 | | * crashed, but there's no need because the next run of this |
4370 | | * function will do that. |
4371 | | */ |
4372 | 0 | if (!StartBackgroundWorker(rw)) |
4373 | 0 | { |
4374 | 0 | StartWorkerNeeded = true; |
4375 | 0 | return; |
4376 | 0 | } |
4377 | | |
4378 | | /* |
4379 | | * If we've launched as many workers as allowed, quit, but have |
4380 | | * ServerLoop call us again to look for additional ready-to-run |
4381 | | * workers. There might not be any, but we'll find out the next |
4382 | | * time we run. |
4383 | | */ |
4384 | 0 | if (++num_launched >= MAX_BGWORKERS_TO_LAUNCH) |
4385 | 0 | { |
4386 | 0 | StartWorkerNeeded = true; |
4387 | 0 | return; |
4388 | 0 | } |
4389 | 0 | } |
4390 | 0 | } |
4391 | 0 | } |
4392 | | |
4393 | | static bool |
4394 | | maybe_reap_io_worker(int pid) |
4395 | 0 | { |
4396 | 0 | for (int i = 0; i < MAX_IO_WORKERS; ++i) |
4397 | 0 | { |
4398 | 0 | if (io_worker_children[i] && |
4399 | 0 | io_worker_children[i]->pid == pid) |
4400 | 0 | { |
4401 | 0 | ReleasePostmasterChildSlot(io_worker_children[i]); |
4402 | |
|
4403 | 0 | --io_worker_count; |
4404 | 0 | io_worker_children[i] = NULL; |
4405 | 0 | return true; |
4406 | 0 | } |
4407 | 0 | } |
4408 | 0 | return false; |
4409 | 0 | } |
4410 | | |
4411 | | /* |
4412 | | * Returns the next time at which maybe_start_io_workers() would start one or |
4413 | | * more I/O workers. Any time in the past means ASAP, and 0 means no worker |
4414 | | * is currently scheduled. |
4415 | | * |
4416 | | * This is called by DetermineSleepTime() and also maybe_start_io_workers() |
4417 | | * itself, to make sure that they agree. |
4418 | | */ |
4419 | | static TimestampTz |
4420 | | maybe_start_io_workers_scheduled_at(void) |
4421 | 0 | { |
4422 | 0 | if (!pgaio_workers_enabled()) |
4423 | 0 | return 0; |
4424 | | |
4425 | | /* |
4426 | | * If we're in final shutting down state, then we're just waiting for all |
4427 | | * processes to exit. |
4428 | | */ |
4429 | 0 | if (pmState >= PM_WAIT_IO_WORKERS) |
4430 | 0 | return 0; |
4431 | | |
4432 | | /* Don't start new workers during an immediate shutdown either. */ |
4433 | 0 | if (Shutdown >= ImmediateShutdown) |
4434 | 0 | return 0; |
4435 | | |
4436 | | /* |
4437 | | * Don't start new workers if we're in the shutdown phase of a crash |
4438 | | * restart. But we *do* need to start if we're already starting up again. |
4439 | | */ |
4440 | 0 | if (FatalError && pmState >= PM_STOP_BACKENDS) |
4441 | 0 | return 0; |
4442 | | |
4443 | | /* |
4444 | | * Don't start a worker if we're at or above the maximum. (Excess workers |
4445 | | * exit when the GUC is lowered, but the count can be temporarily too high |
4446 | | * until they are reaped.) |
4447 | | */ |
4448 | 0 | if (io_worker_count >= io_max_workers) |
4449 | 0 | return 0; |
4450 | | |
4451 | | /* If we're under the minimum, start a worker as soon as possible. */ |
4452 | 0 | if (io_worker_count < io_min_workers) |
4453 | 0 | return TIMESTAMP_MINUS_INFINITY; /* start worker ASAP */ |
4454 | | |
4455 | | /* Only proceed if a "grow" signal has been received from a worker. */ |
4456 | 0 | if (!pgaio_worker_pm_test_grow_signal_sent()) |
4457 | 0 | return 0; |
4458 | | |
4459 | | /* |
4460 | | * maybe_start_io_workers() should start a new I/O worker after this time, |
4461 | | * or as soon as possible if is already in the past. |
4462 | | */ |
4463 | 0 | return io_worker_launch_next_time; |
4464 | 0 | } |
4465 | | |
4466 | | /* |
4467 | | * Start I/O workers if required. Used at startup, to respond to change of |
4468 | | * the io_min_workers GUC, when asked to start a new one due to submission |
4469 | | * queue backlog, and after workers terminate in response to errors (by |
4470 | | * starting "replacement" workers). |
4471 | | */ |
4472 | | static void |
4473 | | maybe_start_io_workers(void) |
4474 | 0 | { |
4475 | 0 | TimestampTz scheduled_at; |
4476 | |
|
4477 | 0 | while ((scheduled_at = maybe_start_io_workers_scheduled_at()) != 0) |
4478 | 0 | { |
4479 | 0 | TimestampTz now = GetCurrentTimestamp(); |
4480 | 0 | PMChild *child; |
4481 | 0 | int i; |
4482 | |
|
4483 | 0 | Assert(pmState < PM_WAIT_IO_WORKERS); |
4484 | | |
4485 | | /* Still waiting for the scheduled time? */ |
4486 | 0 | if (scheduled_at > now) |
4487 | 0 | break; |
4488 | | |
4489 | | /* |
4490 | | * Compute next launch time relative to the previous value, so that |
4491 | | * time spent on the postmaster's other duties don't result in an |
4492 | | * inaccurate launch interval. |
4493 | | */ |
4494 | 0 | io_worker_launch_next_time = |
4495 | 0 | TimestampTzPlusMilliseconds(io_worker_launch_next_time, |
4496 | 0 | io_worker_launch_interval); |
4497 | | |
4498 | | /* |
4499 | | * If that's already in the past, the interval is either impossibly |
4500 | | * short or we received no requests for new workers for a period. |
4501 | | * Compute a new future time relative to now instead. |
4502 | | */ |
4503 | 0 | if (io_worker_launch_next_time <= now) |
4504 | 0 | io_worker_launch_next_time = |
4505 | 0 | TimestampTzPlusMilliseconds(now, io_worker_launch_interval); |
4506 | | |
4507 | | /* |
4508 | | * Check if a grow signal has been received, but the grow request has |
4509 | | * been canceled since then because work ran out. We've still |
4510 | | * advanced the next launch time, to suppress repeat signals from |
4511 | | * workers until then. |
4512 | | */ |
4513 | 0 | if (io_worker_count >= io_min_workers && !pgaio_worker_pm_test_grow()) |
4514 | 0 | { |
4515 | 0 | pgaio_worker_pm_clear_grow_signal_sent(); |
4516 | 0 | break; |
4517 | 0 | } |
4518 | | |
4519 | | /* find unused entry in io_worker_children array */ |
4520 | 0 | for (i = 0; i < MAX_IO_WORKERS; ++i) |
4521 | 0 | { |
4522 | 0 | if (io_worker_children[i] == NULL) |
4523 | 0 | break; |
4524 | 0 | } |
4525 | 0 | if (i == MAX_IO_WORKERS) |
4526 | 0 | elog(ERROR, "could not find a free IO worker slot"); |
4527 | | |
4528 | | /* Try to launch one. */ |
4529 | 0 | child = StartChildProcess(B_IO_WORKER); |
4530 | 0 | if (child != NULL) |
4531 | 0 | { |
4532 | 0 | io_worker_children[i] = child; |
4533 | 0 | ++io_worker_count; |
4534 | 0 | } |
4535 | 0 | else |
4536 | 0 | { |
4537 | | /* |
4538 | | * Fork failure: we'll try again after the launch interval |
4539 | | * expires, or be called again without delay if we don't yet have |
4540 | | * io_min_workers. Don't loop here though, the postmaster has |
4541 | | * other duties. |
4542 | | */ |
4543 | 0 | break; |
4544 | 0 | } |
4545 | 0 | } |
4546 | | |
4547 | | /* |
4548 | | * Workers decide when to shut down by themselves, according to the |
4549 | | * io_max_workers and io_worker_idle_timeout GUCs. |
4550 | | */ |
4551 | 0 | } |
4552 | | |
4553 | | |
4554 | | /* |
4555 | | * When a backend asks to be notified about worker state changes, we |
4556 | | * set a flag in its backend entry. The background worker machinery needs |
4557 | | * to know when such backends exit. |
4558 | | */ |
4559 | | bool |
4560 | | PostmasterMarkPIDForWorkerNotify(int pid) |
4561 | 0 | { |
4562 | 0 | dlist_iter iter; |
4563 | 0 | PMChild *bp; |
4564 | |
|
4565 | 0 | dlist_foreach(iter, &ActiveChildList) |
4566 | 0 | { |
4567 | 0 | bp = dlist_container(PMChild, elem, iter.cur); |
4568 | 0 | if (bp->pid == pid) |
4569 | 0 | { |
4570 | 0 | bp->bgworker_notify = true; |
4571 | 0 | return true; |
4572 | 0 | } |
4573 | 0 | } |
4574 | 0 | return false; |
4575 | 0 | } |
4576 | | |
4577 | | #ifdef WIN32 |
4578 | | |
4579 | | /* |
4580 | | * Subset implementation of waitpid() for Windows. We assume pid is -1 |
4581 | | * (that is, check all child processes) and options is WNOHANG (don't wait). |
4582 | | */ |
4583 | | static pid_t |
4584 | | waitpid(pid_t pid, int *exitstatus, int options) |
4585 | | { |
4586 | | win32_deadchild_waitinfo *childinfo; |
4587 | | DWORD exitcode; |
4588 | | DWORD dwd; |
4589 | | ULONG_PTR key; |
4590 | | OVERLAPPED *ovl; |
4591 | | |
4592 | | /* Try to consume one win32_deadchild_waitinfo from the queue. */ |
4593 | | if (!GetQueuedCompletionStatus(win32ChildQueue, &dwd, &key, &ovl, 0)) |
4594 | | { |
4595 | | errno = EAGAIN; |
4596 | | return -1; |
4597 | | } |
4598 | | |
4599 | | childinfo = (win32_deadchild_waitinfo *) key; |
4600 | | pid = childinfo->procId; |
4601 | | |
4602 | | /* |
4603 | | * Remove handle from wait - required even though it's set to wait only |
4604 | | * once |
4605 | | */ |
4606 | | UnregisterWaitEx(childinfo->waitHandle, NULL); |
4607 | | |
4608 | | if (!GetExitCodeProcess(childinfo->procHandle, &exitcode)) |
4609 | | { |
4610 | | /* |
4611 | | * Should never happen. Inform user and set a fixed exitcode. |
4612 | | */ |
4613 | | write_stderr("could not read exit code for process\n"); |
4614 | | exitcode = 255; |
4615 | | } |
4616 | | *exitstatus = exitcode; |
4617 | | |
4618 | | /* |
4619 | | * Close the process handle. Only after this point can the PID can be |
4620 | | * recycled by the kernel. |
4621 | | */ |
4622 | | CloseHandle(childinfo->procHandle); |
4623 | | |
4624 | | /* |
4625 | | * Free struct that was allocated before the call to |
4626 | | * RegisterWaitForSingleObject() |
4627 | | */ |
4628 | | pfree(childinfo); |
4629 | | |
4630 | | return pid; |
4631 | | } |
4632 | | |
4633 | | /* |
4634 | | * Note! Code below executes on a thread pool! All operations must |
4635 | | * be thread safe! Note that elog() and friends must *not* be used. |
4636 | | */ |
4637 | | static void WINAPI |
4638 | | pgwin32_deadchild_callback(PVOID lpParameter, BOOLEAN TimerOrWaitFired) |
4639 | | { |
4640 | | /* Should never happen, since we use INFINITE as timeout value. */ |
4641 | | if (TimerOrWaitFired) |
4642 | | return; |
4643 | | |
4644 | | /* |
4645 | | * Post the win32_deadchild_waitinfo object for waitpid() to deal with. If |
4646 | | * that fails, we leak the object, but we also leak a whole process and |
4647 | | * get into an unrecoverable state, so there's not much point in worrying |
4648 | | * about that. We'd like to panic, but we can't use that infrastructure |
4649 | | * from this thread. |
4650 | | */ |
4651 | | if (!PostQueuedCompletionStatus(win32ChildQueue, |
4652 | | 0, |
4653 | | (ULONG_PTR) lpParameter, |
4654 | | NULL)) |
4655 | | write_stderr("could not post child completion status\n"); |
4656 | | |
4657 | | /* Queue SIGCHLD signal. */ |
4658 | | pg_queue_signal(SIGCHLD); |
4659 | | } |
4660 | | |
4661 | | /* |
4662 | | * Queue a waiter to signal when this child dies. The wait will be handled |
4663 | | * automatically by an operating system thread pool. The memory and the |
4664 | | * process handle will be freed by a later call to waitpid(). |
4665 | | */ |
4666 | | void |
4667 | | pgwin32_register_deadchild_callback(HANDLE procHandle, DWORD procId) |
4668 | | { |
4669 | | win32_deadchild_waitinfo *childinfo; |
4670 | | |
4671 | | childinfo = palloc_object(win32_deadchild_waitinfo); |
4672 | | childinfo->procHandle = procHandle; |
4673 | | childinfo->procId = procId; |
4674 | | |
4675 | | if (!RegisterWaitForSingleObject(&childinfo->waitHandle, |
4676 | | procHandle, |
4677 | | pgwin32_deadchild_callback, |
4678 | | childinfo, |
4679 | | INFINITE, |
4680 | | WT_EXECUTEONLYONCE | WT_EXECUTEINWAITTHREAD)) |
4681 | | ereport(FATAL, |
4682 | | (errmsg_internal("could not register process for wait: error code %lu", |
4683 | | GetLastError()))); |
4684 | | } |
4685 | | |
4686 | | #endif /* WIN32 */ |
4687 | | |
4688 | | /* |
4689 | | * Initialize one and only handle for monitoring postmaster death. |
4690 | | * |
4691 | | * Called once in the postmaster, so that child processes can subsequently |
4692 | | * monitor if their parent is dead. |
4693 | | */ |
4694 | | static void |
4695 | | InitPostmasterDeathWatchHandle(void) |
4696 | 0 | { |
4697 | 0 | #ifndef WIN32 |
4698 | | |
4699 | | /* |
4700 | | * Create a pipe. Postmaster holds the write end of the pipe open |
4701 | | * (POSTMASTER_FD_OWN), and children hold the read end. Children can pass |
4702 | | * the read file descriptor to select() to wake up in case postmaster |
4703 | | * dies, or check for postmaster death with a (read() == 0). Children must |
4704 | | * close the write end as soon as possible after forking, because EOF |
4705 | | * won't be signaled in the read end until all processes have closed the |
4706 | | * write fd. That is taken care of in ClosePostmasterPorts(). |
4707 | | */ |
4708 | 0 | Assert(MyProcPid == PostmasterPid); |
4709 | 0 | if (pipe(postmaster_alive_fds) < 0) |
4710 | 0 | ereport(FATAL, |
4711 | 0 | (errcode_for_file_access(), |
4712 | 0 | errmsg_internal("could not create pipe to monitor postmaster death: %m"))); |
4713 | | |
4714 | | /* Notify fd.c that we've eaten two FDs for the pipe. */ |
4715 | 0 | ReserveExternalFD(); |
4716 | 0 | ReserveExternalFD(); |
4717 | | |
4718 | | /* |
4719 | | * Set O_NONBLOCK to allow testing for the fd's presence with a read() |
4720 | | * call. |
4721 | | */ |
4722 | 0 | if (fcntl(postmaster_alive_fds[POSTMASTER_FD_WATCH], F_SETFL, O_NONBLOCK) == -1) |
4723 | 0 | ereport(FATAL, |
4724 | 0 | (errcode_for_socket_access(), |
4725 | 0 | errmsg_internal("could not set postmaster death monitoring pipe to nonblocking mode: %m"))); |
4726 | | #else |
4727 | | |
4728 | | /* |
4729 | | * On Windows, we use a process handle for the same purpose. |
4730 | | */ |
4731 | | if (DuplicateHandle(GetCurrentProcess(), |
4732 | | GetCurrentProcess(), |
4733 | | GetCurrentProcess(), |
4734 | | &PostmasterHandle, |
4735 | | 0, |
4736 | | TRUE, |
4737 | | DUPLICATE_SAME_ACCESS) == 0) |
4738 | | ereport(FATAL, |
4739 | | (errmsg_internal("could not duplicate postmaster handle: error code %lu", |
4740 | | GetLastError()))); |
4741 | | #endif /* WIN32 */ |
4742 | 0 | } |