postgresql/src/backend/postmaster/startup.c

255 lines
6.0 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* startup.c
*
* The Startup process initialises the server and performs any recovery
* actions that have been specified. Notice that there is no "main loop"
* since the Startup process ends as soon as initialisation is complete.
Allow a streaming replication standby to follow a timeline switch. Before this patch, streaming replication would refuse to start replicating if the timeline in the primary doesn't exactly match the standby. The situation where it doesn't match is when you have a master, and two standbys, and you promote one of the standbys to become new master. Promoting bumps up the timeline ID, and after that bump, the other standby would refuse to continue. There's significantly more timeline related logic in streaming replication now. First of all, when a standby connects to primary, it will ask the primary for any timeline history files that are missing from the standby. The missing files are sent using a new replication command TIMELINE_HISTORY, and stored in standby's pg_xlog directory. Using the timeline history files, the standby can follow the latest timeline present in the primary (recovery_target_timeline='latest'), just as it can follow new timelines appearing in an archive directory. START_REPLICATION now takes a TIMELINE parameter, to specify exactly which timeline to stream WAL from. This allows the standby to request the primary to send over WAL that precedes the promotion. The replication protocol is changed slightly (in a backwards-compatible way although there's little hope of streaming replication working across major versions anyway), to allow replication to stop when the end of timeline reached, putting the walsender back into accepting a replication command. Many thanks to Amit Kapila for testing and reviewing various versions of this patch.
2012-12-13 18:00:00 +01:00
* (in standby mode, one can think of the replay loop as a main loop,
* though.)
*
*
* Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
*
*
* IDENTIFICATION
* src/backend/postmaster/startup.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <signal.h>
#include <unistd.h>
#include "access/xlog.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "postmaster/startup.h"
#include "storage/ipc.h"
#include "storage/latch.h"
#include "storage/pmsignal.h"
#include "storage/standby.h"
#include "utils/guc.h"
#include "utils/timeout.h"
/*
* Flags set by interrupt handlers for later service in the redo loop.
*/
static volatile sig_atomic_t got_SIGHUP = false;
static volatile sig_atomic_t shutdown_requested = false;
static volatile sig_atomic_t promote_triggered = false;
/*
* Flag set when executing a restore command, to tell SIGTERM signal handler
* that it's safe to just proc_exit.
*/
static volatile sig_atomic_t in_restore_command = false;
/* Signal handlers */
static void startupproc_quickdie(SIGNAL_ARGS);
static void StartupProcSigUsr1Handler(SIGNAL_ARGS);
static void StartupProcTriggerHandler(SIGNAL_ARGS);
static void StartupProcSigHupHandler(SIGNAL_ARGS);
/* --------------------------------
* signal handler routines
* --------------------------------
*/
/*
* startupproc_quickdie() occurs when signalled SIGQUIT by the postmaster.
*
* Some backend has bought the farm,
* so we need to stop what we're doing and exit.
*/
static void
startupproc_quickdie(SIGNAL_ARGS)
{
PG_SETMASK(&BlockSig);
/*
* We DO NOT want to run proc_exit() callbacks -- we're here because
* shared memory may be corrupted, so we don't want to try to clean up our
* transaction. Just nail the windows shut and get out of town. Now that
* there's an atexit callback to prevent third-party code from breaking
* things by calling exit() directly, we have to reset the callbacks
* explicitly to make this work as intended.
*/
on_exit_reset();
/*
* Note we do exit(2) not exit(0). This is to force the postmaster into a
* system reset cycle if some idiot DBA sends a manual SIGQUIT to a random
* backend. This is necessary precisely because we don't clean up our
* shared memory state. (The "dead man switch" mechanism in pmsignal.c
* should ensure the postmaster sees this as a crash, too, but no harm in
* being doubly sure.)
*/
exit(2);
}
/* SIGUSR1: let latch facility handle the signal */
static void
StartupProcSigUsr1Handler(SIGNAL_ARGS)
{
int save_errno = errno;
latch_sigusr1_handler();
errno = save_errno;
}
/* SIGUSR2: set flag to finish recovery */
static void
StartupProcTriggerHandler(SIGNAL_ARGS)
{
int save_errno = errno;
promote_triggered = true;
WakeupRecovery();
errno = save_errno;
}
/* SIGHUP: set flag to re-read config file at next convenient time */
static void
StartupProcSigHupHandler(SIGNAL_ARGS)
{
int save_errno = errno;
got_SIGHUP = true;
WakeupRecovery();
errno = save_errno;
}
/* SIGTERM: set flag to abort redo and exit */
static void
StartupProcShutdownHandler(SIGNAL_ARGS)
{
int save_errno = errno;
if (in_restore_command)
proc_exit(1);
else
shutdown_requested = true;
WakeupRecovery();
errno = save_errno;
}
/* Handle SIGHUP and SIGTERM signals of startup process */
void
HandleStartupProcInterrupts(void)
{
/*
* Check if we were requested to re-read config file.
*/
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
}
/*
* Check if we were requested to exit without finishing recovery.
*/
if (shutdown_requested)
proc_exit(1);
/*
* Emergency bailout if postmaster has died. This is to avoid the
* necessity for manual cleanup of all postmaster children.
*/
if (IsUnderPostmaster && !PostmasterIsAlive())
exit(1);
}
/* ----------------------------------
* Startup Process main entry point
* ----------------------------------
*/
void
StartupProcessMain(void)
{
/*
* Properly accept or ignore signals the postmaster might send us.
*/
pqsignal(SIGHUP, StartupProcSigHupHandler); /* reload config file */
pqsignal(SIGINT, SIG_IGN); /* ignore query cancel */
pqsignal(SIGTERM, StartupProcShutdownHandler); /* request shutdown */
pqsignal(SIGQUIT, startupproc_quickdie); /* hard crash time */
InitializeTimeouts(); /* establishes SIGALRM handler */
pqsignal(SIGPIPE, SIG_IGN);
pqsignal(SIGUSR1, StartupProcSigUsr1Handler);
pqsignal(SIGUSR2, StartupProcTriggerHandler);
/*
* Reset some signals that are accepted by postmaster but not here
*/
pqsignal(SIGCHLD, SIG_DFL);
pqsignal(SIGTTIN, SIG_DFL);
pqsignal(SIGTTOU, SIG_DFL);
pqsignal(SIGCONT, SIG_DFL);
pqsignal(SIGWINCH, SIG_DFL);
/*
* Register timeouts needed for standby mode
*/
RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
/*
* Unblock signals (they were blocked when the postmaster forked us)
*/
PG_SETMASK(&UnBlockSig);
/*
* Do what we came for.
*/
StartupXLOG();
/*
* Exit normally. Exit code 0 tells postmaster that we completed recovery
* successfully.
*/
proc_exit(0);
}
void
PreRestoreCommand(void)
{
/*
* Set in_restore_command to tell the signal handler that we should exit
* right away on SIGTERM. We know that we're at a safe point to do that.
* Check if we had already received the signal, so that we don't miss a
* shutdown request received just before this.
*/
in_restore_command = true;
if (shutdown_requested)
proc_exit(1);
}
void
PostRestoreCommand(void)
{
in_restore_command = false;
}
bool
IsPromoteTriggered(void)
{
return promote_triggered;
}
void
ResetPromoteTriggered(void)
{
promote_triggered = false;
}