1
0
mirror of https://github.com/postgres/postgres.git synced 2025-05-05 09:19:17 +03:00
Heikki Linnakangas 8e4e783ee4 Don't run atexit callbacks in quickdie signal handlers.
exit() is not async-signal safe. Even if the libc implementation is, 3rd
party libraries might have installed unsafe atexit() callbacks. After
receiving SIGQUIT, we really just want to exit as quickly as possible, so
we don't really want to run the atexit() callbacks anyway.

The original report by Jimmy Yih was a self-deadlock in startup_die().
However, this patch doesn't address that scenario; the signal handling
while waiting for the startup packet is more complicated. But at least this
alleviates similar problems in the SIGQUIT handlers, like that reported
by Asim R P later in the same thread.

Backpatch to 9.3 (all supported versions).

Discussion: https://www.postgresql.org/message-id/CAOMx_OAuRUHiAuCg2YgicZLzPVv5d9_H4KrL_OFsFP%3DVPekigA%40mail.gmail.com
2018-08-08 19:09:33 +03:00

250 lines
5.9 KiB
C

/*-------------------------------------------------------------------------
*
* 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.
* (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)
{
/*
* We DO NOT want to run proc_exit() or atexit() 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. The callbacks wouldn't be safe to run from a signal handler,
* anyway.
*
* Note we do _exit(2) not _exit(0). This is to force the postmaster into
* a system reset cycle if someone 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);
RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
/*
* 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;
}