bgwriter.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*-------------------------------------------------------------------------
 *
 * bgwriter.c
 *
 * The background writer (bgwriter) is new in Postgres 8.0.  It attempts
 * to keep regular backends from having to write out dirty shared buffers
 * (which they would only do when needing to free a shared buffer to read in
 * another page).  In the best scenario all writes from shared buffers will
 * be issued by the background writer process.	However, regular backends are
 * still empowered to issue writes if the bgwriter fails to maintain enough
 * clean shared buffers.
 *
 * The bgwriter is also charged with handling all checkpoints.	It will
 * automatically dispatch a checkpoint after a certain amount of time has
 * elapsed since the last one, and it can be signaled to perform requested
 * checkpoints as well.  (The GUC parameter that mandates a checkpoint every
 * so many WAL segments is implemented by having backends signal the bgwriter
 * when they fill WAL segments; the bgwriter itself doesn't watch for the
 * condition.)
 *
 * The bgwriter is started by the postmaster as soon as the startup subprocess
 * finishes.  It remains alive until the postmaster commands it to terminate.
 * Normal termination is by SIGUSR2, which instructs the bgwriter to execute
 * a shutdown checkpoint and then exit(0).	(All backends must be stopped
 * before SIGUSR2 is issued!)  Emergency termination is by SIGQUIT; like any
 * backend, the bgwriter will simply abort and exit on SIGQUIT.
 *
 * If the bgwriter exits unexpectedly, the postmaster treats that the same
 * as a backend crash: shared memory may be corrupted, so remaining backends
 * should be killed by SIGQUIT and then a recovery cycle started.  (Even if
 * shared memory isn't corrupted, we have lost information about which
 * files need to be fsync'd for the next checkpoint, and so a system
 * restart needs to be forced.)
 *
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.21.2.1 2005/12/08 19:19:31 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <signal.h>
#include <time.h>

#include "access/xlog.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "postmaster/bgwriter.h"
#include "storage/bufmgr.h"
#include "storage/fd.h"
#include "storage/freespace.h"
#include "storage/ipc.h"
#include "storage/pmsignal.h"
#include "storage/smgr.h"
#include "tcop/tcopprot.h"
#include "utils/guc.h"
#include "utils/memutils.h"
#include "utils/resowner.h"


/*----------
 * Shared memory area for communication between bgwriter and backends
 *
 * The ckpt counters allow backends to watch for completion of a checkpoint
 * request they send.  Here's how it works:
 *	* At start of a checkpoint, bgwriter increments ckpt_started.
 *	* On completion of a checkpoint, bgwriter sets ckpt_done to
 *	  equal ckpt_started.
 *	* On failure of a checkpoint, bgwrite first increments ckpt_failed,
 *	  then sets ckpt_done to equal ckpt_started.
 * All three fields are declared sig_atomic_t to ensure they can be read
 * and written without explicit locking.  The algorithm for backends is:
 *	1. Record current values of ckpt_failed and ckpt_started (in that
 *	   order!).
 *	2. Send signal to request checkpoint.
 *	3. Sleep until ckpt_started changes.  Now you know a checkpoint has
 *	   begun since you started this algorithm (although *not* that it was
 *	   specifically initiated by your signal).
 *	4. Record new value of ckpt_started.
 *	5. Sleep until ckpt_done >= saved value of ckpt_started.  (Use modulo
 *	   arithmetic here in case counters wrap around.)  Now you know a
 *	   checkpoint has started and completed, but not whether it was
 *	   successful.
 *	6. If ckpt_failed is different from the originally saved value,
 *	   assume request failed; otherwise it was definitely successful.
 *
 * An additional field is ckpt_time_warn; this is also sig_atomic_t for
 * simplicity, but is only used as a boolean.  If a backend is requesting
 * a checkpoint for which a checkpoints-too-close-together warning is
 * reasonable, it should set this field TRUE just before sending the signal.
 *
 * The requests array holds fsync requests sent by backends and not yet
 * absorbed by the bgwriter.  Unlike the checkpoint fields, the requests
 * fields are protected by BgWriterCommLock.
 *----------
 */
typedef struct
{
	RelFileNode rnode;
	BlockNumber segno;
	/* might add a request-type field later */
} BgWriterRequest;

typedef struct
{
	pid_t		bgwriter_pid;	/* PID of bgwriter (0 if not started) */

	sig_atomic_t ckpt_started;	/* advances when checkpoint starts */
	sig_atomic_t ckpt_done;		/* advances when checkpoint done */
	sig_atomic_t ckpt_failed;	/* advances when checkpoint fails */

	sig_atomic_t ckpt_time_warn;	/* warn if too soon since last ckpt? */

	int			num_requests;	/* current # of requests */
	int			max_requests;	/* allocated array size */
	BgWriterRequest requests[1];	/* VARIABLE LENGTH ARRAY */
} BgWriterShmemStruct;

static BgWriterShmemStruct *BgWriterShmem;

/*
 * GUC parameters
 */
int			BgWriterDelay = 200;
int			CheckPointTimeout = 300;
int			CheckPointWarning = 30;

/*
 * Flags set by interrupt handlers for later service in the main loop.
 */
static volatile sig_atomic_t got_SIGHUP = false;
static volatile sig_atomic_t checkpoint_requested = false;
static volatile sig_atomic_t shutdown_requested = false;

/*
 * Private state
 */
static bool am_bg_writer = false;

static bool ckpt_active = false;

static time_t last_checkpoint_time;


static void bg_quickdie(SIGNAL_ARGS);
static void BgSigHupHandler(SIGNAL_ARGS);
static void ReqCheckpointHandler(SIGNAL_ARGS);
static void ReqShutdownHandler(SIGNAL_ARGS);


/*
 * Main entry point for bgwriter process
 *
 * This is invoked from BootstrapMain, which has already created the basic
 * execution environment, but not enabled signals yet.
 */
void
BackgroundWriterMain(void)
{
	sigjmp_buf	local_sigjmp_buf;
	MemoryContext bgwriter_context;

	Assert(BgWriterShmem != NULL);
	BgWriterShmem->bgwriter_pid = MyProcPid;
	am_bg_writer = true;

	/*
	 * Properly accept or ignore signals the postmaster might send us
	 *
	 * Note: we deliberately ignore SIGTERM, because during a standard Unix
	 * system shutdown cycle, init will SIGTERM all processes at once.	We
	 * want to wait for the backends to exit, whereupon the postmaster will
	 * tell us it's okay to shut down (via SIGUSR2).
	 *
	 * SIGUSR1 is presently unused; keep it spare in case someday we want this
	 * process to participate in sinval messaging.
	 */
	pqsignal(SIGHUP, BgSigHupHandler);	/* set flag to read config file */
	pqsignal(SIGINT, ReqCheckpointHandler);		/* request checkpoint */
	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
	pqsignal(SIGQUIT, bg_quickdie);		/* hard crash time */
	pqsignal(SIGALRM, SIG_IGN);
	pqsignal(SIGPIPE, SIG_IGN);
	pqsignal(SIGUSR1, SIG_IGN); /* reserve for sinval */
	pqsignal(SIGUSR2, ReqShutdownHandler);		/* request shutdown */

	/*
	 * 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);

	/* We allow SIGQUIT (quickdie) at all times */
#ifdef HAVE_SIGPROCMASK
	sigdelset(&BlockSig, SIGQUIT);
#else
	BlockSig &= ~(sigmask(SIGQUIT));
#endif

	/*
	 * Initialize so that first time-driven checkpoint happens at the correct
	 * time.
	 */
	last_checkpoint_time = time(NULL);

	/*
	 * Create a resource owner to keep track of our resources (currently
	 * only buffer pins).
	 */
	CurrentResourceOwner = ResourceOwnerCreate(NULL, "Background Writer");

	/*
	 * Create a memory context that we will do all our work in.  We do this so
	 * that we can reset the context during error recovery and thereby avoid
	 * possible memory leaks.  Formerly this code just ran in
	 * TopMemoryContext, but resetting that would be a really bad idea.
	 */
	bgwriter_context = AllocSetContextCreate(TopMemoryContext,
											 "Background Writer",
											 ALLOCSET_DEFAULT_MINSIZE,
											 ALLOCSET_DEFAULT_INITSIZE,
											 ALLOCSET_DEFAULT_MAXSIZE);
	MemoryContextSwitchTo(bgwriter_context);

	/*
	 * If an exception is encountered, processing resumes here.
	 *
	 * See notes in postgres.c about the design of this coding.
	 */
	if (sigsetjmp(local_sigjmp_buf, 1) != 0)
	{
		/* Since not using PG_TRY, must reset error stack by hand */
		error_context_stack = NULL;

		/* Prevent interrupts while cleaning up */
		HOLD_INTERRUPTS();

		/* Report the error to the server log */
		EmitErrorReport();

		/*
		 * These operations are really just a minimal subset of
		 * AbortTransaction().	We don't have very many resources to worry
		 * about in bgwriter, but we do have LWLocks, buffers, and temp files.
		 */
		LWLockReleaseAll();
		AbortBufferIO();
		UnlockBuffers();
		/* buffer pins are released here: */
		ResourceOwnerRelease(CurrentResourceOwner,
							 RESOURCE_RELEASE_BEFORE_LOCKS,
							 false, true);
		/* we needn't bother with the other ResourceOwnerRelease phases */
		AtEOXact_Buffers(false);
		AtEOXact_Files();

		/* Warn any waiting backends that the checkpoint failed. */
		if (ckpt_active)
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile BgWriterShmemStruct *bgs = BgWriterShmem;

			bgs->ckpt_failed++;
			bgs->ckpt_done = bgs->ckpt_started;
			ckpt_active = false;
		}

		/*
		 * Now return to normal top-level context and clear ErrorContext for
		 * next time.
		 */
		MemoryContextSwitchTo(bgwriter_context);
		FlushErrorState();

		/* Flush any leaked data in the top-level context */
		MemoryContextResetAndDeleteChildren(bgwriter_context);

		/* Now we can allow interrupts again */
		RESUME_INTERRUPTS();

		/*
		 * Sleep at least 1 second after any error.  A write error is likely
		 * to be repeated, and we don't want to be filling the error logs as
		 * fast as we can.
		 */
		pg_usleep(1000000L);
	}

	/* We can now handle ereport(ERROR) */
	PG_exception_stack = &local_sigjmp_buf;

	/*
	 * Unblock signals (they were blocked when the postmaster forked us)
	 */
	PG_SETMASK(&UnBlockSig);

	/*
	 * Loop forever
	 */
	for (;;)
	{
		bool		do_checkpoint = false;
		bool		force_checkpoint = false;
		time_t		now;
		int			elapsed_secs;
		long		udelay;

		/*
		 * Emergency bailout if postmaster has died.  This is to avoid the
		 * necessity for manual cleanup of all postmaster children.
		 */
		if (!PostmasterIsAlive(true))
			exit(1);

		/*
		 * Process any requests or signals received recently.
		 */
		AbsorbFsyncRequests();

		if (got_SIGHUP)
		{
			got_SIGHUP = false;
			ProcessConfigFile(PGC_SIGHUP);
		}
		if (checkpoint_requested)
		{
			checkpoint_requested = false;
			do_checkpoint = true;
			force_checkpoint = true;
		}
		if (shutdown_requested)
		{
			ShutdownXLOG(0, 0);
			DumpFreeSpaceMap(0, 0);
			/* Normal exit from the bgwriter is here */
			proc_exit(0);		/* done */
		}

		/*
		 * Do an unforced checkpoint if too much time has elapsed since the
		 * last one.
		 */
		now = time(NULL);
		elapsed_secs = now - last_checkpoint_time;
		if (elapsed_secs >= CheckPointTimeout)
			do_checkpoint = true;

		/*
		 * Do a checkpoint if requested, otherwise do one cycle of
		 * dirty-buffer writing.