bgwriter.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

		 */
		if (do_checkpoint)
		{
			/*
			 * We will warn if (a) too soon since last checkpoint (whatever
			 * caused it) and (b) somebody has set the ckpt_time_warn flag
			 * since the last checkpoint start.  Note in particular that this
			 * implementation will not generate warnings caused by
			 * CheckPointTimeout < CheckPointWarning.
			 */
			if (BgWriterShmem->ckpt_time_warn &&
				elapsed_secs < CheckPointWarning)
				ereport(LOG,
						(errmsg("checkpoints are occurring too frequently (%d seconds apart)",
								elapsed_secs),
						 errhint("Consider increasing the configuration parameter \"checkpoint_segments\".")));
			BgWriterShmem->ckpt_time_warn = false;

			/*
			 * Indicate checkpoint start to any waiting backends.
			 */
			ckpt_active = true;
			BgWriterShmem->ckpt_started++;

			CreateCheckPoint(false, force_checkpoint);

			/*
			 * After any checkpoint, close all smgr files.	This is so we
			 * won't hang onto smgr references to deleted files indefinitely.
			 */
			smgrcloseall();

			/*
			 * Indicate checkpoint completion to any waiting backends.
			 */
			BgWriterShmem->ckpt_done = BgWriterShmem->ckpt_started;
			ckpt_active = false;

			/*
			 * Note we record the checkpoint start time not end time as
			 * last_checkpoint_time.  This is so that time-driven checkpoints
			 * happen at a predictable spacing.
			 */
			last_checkpoint_time = now;
		}
		else
			BgBufferSync();

		/*
		 * Nap for the configured time, or sleep for 10 seconds if there is no
		 * bgwriter activity configured.
		 *
		 * On some platforms, signals won't interrupt the sleep.  To ensure we
		 * respond reasonably promptly when someone signals us, break down the
		 * sleep into 1-second increments, and check for interrupts after each
		 * nap.
		 *
		 * We absorb pending requests after each short sleep.
		 */
		if ((bgwriter_all_percent > 0.0 && bgwriter_all_maxpages > 0) ||
			(bgwriter_lru_percent > 0.0 && bgwriter_lru_maxpages > 0))
			udelay = BgWriterDelay * 1000L;
		else
			udelay = 10000000L;
		while (udelay > 1000000L)
		{
			if (got_SIGHUP || checkpoint_requested || shutdown_requested)
				break;
			pg_usleep(1000000L);
			AbsorbFsyncRequests();
			udelay -= 1000000L;
		}
		if (!(got_SIGHUP || checkpoint_requested || shutdown_requested))
			pg_usleep(udelay);
	}
}


/* --------------------------------
 *		signal handler routines
 * --------------------------------
 */

/*
 * bg_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
bg_quickdie(SIGNAL_ARGS)
{
	PG_SETMASK(&BlockSig);

	/*
	 * DO NOT proc_exit() -- 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.
	 *
	 * Note we do exit(1) 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.
	 */
	exit(1);
}

/* SIGHUP: set flag to re-read config file at next convenient time */
static void
BgSigHupHandler(SIGNAL_ARGS)
{
	got_SIGHUP = true;
}

/* SIGINT: set flag to run a normal checkpoint right away */
static void
ReqCheckpointHandler(SIGNAL_ARGS)
{
	checkpoint_requested = true;
}

/* SIGUSR2: set flag to run a shutdown checkpoint and exit */
static void
ReqShutdownHandler(SIGNAL_ARGS)
{
	shutdown_requested = true;
}


/* --------------------------------
 *		communication with backends
 * --------------------------------
 */

/*
 * BgWriterShmemSize
 *		Compute space needed for bgwriter-related shared memory
 */
Size
BgWriterShmemSize(void)
{
	Size		size;

	/*
	 * Currently, the size of the requests[] array is arbitrarily set equal to
	 * NBuffers.  This may prove too large or small ...
	 */
	size = offsetof(BgWriterShmemStruct, requests);
	size = add_size(size, mul_size(NBuffers, sizeof(BgWriterRequest)));

	return size;
}

/*
 * BgWriterShmemInit
 *		Allocate and initialize bgwriter-related shared memory
 */
void
BgWriterShmemInit(void)
{
	bool		found;

	BgWriterShmem = (BgWriterShmemStruct *)
		ShmemInitStruct("Background Writer Data",
						BgWriterShmemSize(),
						&found);
	if (BgWriterShmem == NULL)
		ereport(FATAL,
				(errcode(ERRCODE_OUT_OF_MEMORY),
				 errmsg("not enough shared memory for background writer")));
	if (found)
		return;					/* already initialized */

	MemSet(BgWriterShmem, 0, sizeof(BgWriterShmemStruct));
	BgWriterShmem->max_requests = NBuffers;
}

/*
 * RequestCheckpoint
 *		Called in backend processes to request an immediate checkpoint
 *
 * If waitforit is true, wait until the checkpoint is completed
 * before returning; otherwise, just signal the request and return
 * immediately.
 *
 * If warnontime is true, and it's "too soon" since the last checkpoint,
 * the bgwriter will log a warning.  This should be true only for checkpoints
 * caused due to xlog filling, else the warning will be misleading.
 */
void
RequestCheckpoint(bool waitforit, bool warnontime)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile BgWriterShmemStruct *bgs = BgWriterShmem;
	sig_atomic_t old_failed = bgs->ckpt_failed;
	sig_atomic_t old_started = bgs->ckpt_started;

	/*
	 * If in a standalone backend, just do it ourselves.
	 */
	if (!IsPostmasterEnvironment)
	{
		CreateCheckPoint(false, true);

		/*
		 * After any checkpoint, close all smgr files.	This is so we won't
		 * hang onto smgr references to deleted files indefinitely.
		 */
		smgrcloseall();

		return;
	}

	/* Set warning request flag if appropriate */
	if (warnontime)
		bgs->ckpt_time_warn = true;

	/*
	 * Send signal to request checkpoint.  When waitforit is false, we
	 * consider failure to send the signal to be nonfatal.
	 */
	if (BgWriterShmem->bgwriter_pid == 0)
		elog(waitforit ? ERROR : LOG,
			 "could not request checkpoint because bgwriter not running");
	if (kill(BgWriterShmem->bgwriter_pid, SIGINT) != 0)
		elog(waitforit ? ERROR : LOG,
			 "could not signal for checkpoint: %m");

	/*
	 * If requested, wait for completion.  We detect completion according to
	 * the algorithm given above.
	 */
	if (waitforit)
	{
		while (bgs->ckpt_started == old_started)
		{
			CHECK_FOR_INTERRUPTS();
			pg_usleep(100000L);
		}
		old_started = bgs->ckpt_started;

		/*
		 * We are waiting for ckpt_done >= old_started, in a modulo sense.
		 * This is a little tricky since we don't know the width or signedness
		 * of sig_atomic_t.  We make the lowest common denominator assumption
		 * that it is only as wide as "char".  This means that this algorithm
		 * will cope correctly as long as we don't sleep for more than 127
		 * completed checkpoints.  (If we do, we will get another chance to
		 * exit after 128 more checkpoints...)
		 */
		while (((signed char) (bgs->ckpt_done - old_started)) < 0)
		{
			CHECK_FOR_INTERRUPTS();
			pg_usleep(100000L);
		}
		if (bgs->ckpt_failed != old_failed)
			ereport(ERROR,
					(errmsg("checkpoint request failed"),
					 errhint("Consult the server log for details.")));
	}
}

/*
 * ForwardFsyncRequest
 *		Forward a file-fsync request from a backend to the bgwriter
 *
 * Whenever a backend is compelled to write directly to a relation
 * (which should be seldom, if the bgwriter is getting its job done),
 * the backend calls this routine to pass over knowledge that the relation
 * is dirty and must be fsync'd before next checkpoint.
 *
 * If we are unable to pass over the request (at present, this can happen
 * if the shared memory queue is full), we return false.  That forces
 * the backend to do its own fsync.  We hope that will be even more seldom.
 *
 * Note: we presently make no attempt to eliminate duplicate requests
 * in the requests[] queue.  The bgwriter will have to eliminate dups
 * internally anyway, so we may as well avoid holding the lock longer
 * than we have to here.
 */
bool
ForwardFsyncRequest(RelFileNode rnode, BlockNumber segno)
{
	BgWriterRequest *request;

	if (!IsUnderPostmaster)
		return false;			/* probably shouldn't even get here */
	Assert(BgWriterShmem != NULL);

	LWLockAcquire(BgWriterCommLock, LW_EXCLUSIVE);
	if (BgWriterShmem->bgwriter_pid == 0 ||
		BgWriterShmem->num_requests >= BgWriterShmem->max_requests)
	{
		LWLockRelease(BgWriterCommLock);
		return false;
	}
	request = &BgWriterShmem->requests[BgWriterShmem->num_requests++];
	request->rnode = rnode;
	request->segno = segno;
	LWLockRelease(BgWriterCommLock);
	return true;
}

/*
 * AbsorbFsyncRequests
 *		Retrieve queued fsync requests and pass them to local smgr.
 *
 * This is exported because it must be called during CreateCheckPoint;
 * we have to be sure we have accepted all pending requests *after* we
 * establish the checkpoint REDO pointer.  Since CreateCheckPoint
 * sometimes runs in non-bgwriter processes, do nothing if not bgwriter.
 */
void
AbsorbFsyncRequests(void)
{
	BgWriterRequest *requests = NULL;
	BgWriterRequest *request;
	int			n;

	if (!am_bg_writer)
		return;

	/*
	 * We have to PANIC if we fail to absorb all the pending requests (eg,
	 * because our hashtable runs out of memory).  This is because the system
	 * cannot run safely if we are unable to fsync what we have been told to
	 * fsync.  Fortunately, the hashtable is so small that the problem is
	 * quite unlikely to arise in practice.
	 */
	START_CRIT_SECTION();

	/*
	 * We try to avoid holding the lock for a long time by copying the request
	 * array.
	 */
	LWLockAcquire(BgWriterCommLock, LW_EXCLUSIVE);

	n = BgWriterShmem->num_requests;
	if (n > 0)
	{
		requests = (BgWriterRequest *) palloc(n * sizeof(BgWriterRequest));
		memcpy(requests, BgWriterShmem->requests, n * sizeof(BgWriterRequest));
	}
	BgWriterShmem->num_requests = 0;

	LWLockRelease(BgWriterCommLock);

	for (request = requests; n > 0; request++, n--)
		RememberFsyncRequest(request->rnode, request->segno);

	if (requests)
		pfree(requests);

	END_CRIT_SECTION();
}