postgres/src/backend/access/transam/timeline.c

/*-------------------------------------------------------------------------
 *
 * timeline.c
 *		Functions for reading and writing timeline history files.
 *
 * A timeline history file lists the timeline changes of the timeline, in
 * a simple text format. They are archived along with the WAL segments.
 *
 * The files are named like "<tli>.history". For example, if the database
 * starts up and switches to timeline 5, the timeline history file would be
 * called "00000005.history".
 *
 * Each line in the file represents a timeline switch:
 *
 * <parentTLI> <xlogfname> <reason>
 *
 *	parentTLI	ID of the parent timeline
 *	xlogfname	filename of the WAL segment where the switch happened
 *	reason		human-readable explanation of why the timeline was changed
 *
 * The fields are separated by tabs. Lines beginning with # are comments, and
 * are ignored. Empty lines are also ignored.
 *
 * Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/backend/access/transam/timeline.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include <sys/stat.h>
#include <stdio.h>
#include <unistd.h>

#include "access/timeline.h"
#include "access/xlog_internal.h"
#include "access/xlogdefs.h"
#include "storage/fd.h"

/*
 * Try to read a timeline's history file.
 *
 * If successful, return the list of component TLIs (the given TLI followed by
 * its ancestor TLIs).	If we can't find the history file, assume that the
 * timeline has no parents, and return a list of just the specified timeline
 * ID.
 */
List *
readTimeLineHistory(TimeLineID targetTLI)
{
	List	   *result;
	char		path[MAXPGPATH];
	char		histfname[MAXFNAMELEN];
	char		fline[MAXPGPATH];
	FILE	   *fd;

	/* Timeline 1 does not have a history file, so no need to check */
	if (targetTLI == 1)
		return list_make1_int((int) targetTLI);

	if (InArchiveRecovery)
	{
		TLHistoryFileName(histfname, targetTLI);
		RestoreArchivedFile(path, histfname, "RECOVERYHISTORY", 0, false);
	}
	else
		TLHistoryFilePath(path, targetTLI);

	fd = AllocateFile(path, "r");
	if (fd == NULL)
	{
		if (errno != ENOENT)
			ereport(FATAL,
					(errcode_for_file_access(),
					 errmsg("could not open file \"%s\": %m", path)));
		/* Not there, so assume no parents */
		return list_make1_int((int) targetTLI);
	}

	result = NIL;

	/*
	 * Parse the file...
	 */
	while (fgets(fline, sizeof(fline), fd) != NULL)
	{
		/* skip leading whitespace and check for # comment */
		char	   *ptr;
		char	   *endptr;
		TimeLineID	tli;

		for (ptr = fline; *ptr; ptr++)
		{
			if (!isspace((unsigned char) *ptr))
				break;
		}
		if (*ptr == '\0' || *ptr == '#')
			continue;

		/* expect a numeric timeline ID as first field of line */
		tli = (TimeLineID) strtoul(ptr, &endptr, 0);
		if (endptr == ptr)
			ereport(FATAL,
					(errmsg("syntax error in history file: %s", fline),
					 errhint("Expected a numeric timeline ID.")));

		if (result &&
			tli <= (TimeLineID) linitial_int(result))
			ereport(FATAL,
					(errmsg("invalid data in history file: %s", fline),
				   errhint("Timeline IDs must be in increasing sequence.")));

		/* Build list with newest item first */
		result = lcons_int((int) tli, result);

		/* we ignore the remainder of each line */
	}

	FreeFile(fd);

	if (result &&
		targetTLI <= (TimeLineID) linitial_int(result))
		ereport(FATAL,
				(errmsg("invalid data in history file \"%s\"", path),
			errhint("Timeline IDs must be less than child timeline's ID.")));

	result = lcons_int((int) targetTLI, result);

	ereport(DEBUG3,
			(errmsg_internal("history of timeline %u is %s",
							 targetTLI, nodeToString(result))));

	return result;
}

/*
 * Probe whether a timeline history file exists for the given timeline ID
 */
bool
existsTimeLineHistory(TimeLineID probeTLI)
{
	char		path[MAXPGPATH];
	char		histfname[MAXFNAMELEN];
	FILE	   *fd;

	/* Timeline 1 does not have a history file, so no need to check */
	if (probeTLI == 1)
		return false;

	if (InArchiveRecovery)
	{
		TLHistoryFileName(histfname, probeTLI);
		RestoreArchivedFile(path, histfname, "RECOVERYHISTORY", 0, false);
	}
	else
		TLHistoryFilePath(path, probeTLI);

	fd = AllocateFile(path, "r");
	if (fd != NULL)
	{
		FreeFile(fd);
		return true;
	}
	else
	{
		if (errno != ENOENT)
			ereport(FATAL,
					(errcode_for_file_access(),
					 errmsg("could not open file \"%s\": %m", path)));
		return false;
	}
}

/*
 * Find the newest existing timeline, assuming that startTLI exists.
 *
 * Note: while this is somewhat heuristic, it does positively guarantee
 * that (result + 1) is not a known timeline, and therefore it should
 * be safe to assign that ID to a new timeline.
 */
TimeLineID
findNewestTimeLine(TimeLineID startTLI)
{
	TimeLineID	newestTLI;
	TimeLineID	probeTLI;

	/*
	 * The algorithm is just to probe for the existence of timeline history
	 * files.  XXX is it useful to allow gaps in the sequence?
	 */
	newestTLI = startTLI;

	for (probeTLI = startTLI + 1;; probeTLI++)
	{
		if (existsTimeLineHistory(probeTLI))
		{
			newestTLI = probeTLI;		/* probeTLI exists */
		}
		else
		{
			/* doesn't exist, assume we're done */
			break;
		}
	}

	return newestTLI;
}

/*
 * Create a new timeline history file.
 *
 *	newTLI: ID of the new timeline
 *	parentTLI: ID of its immediate parent
 *	endTLI et al: ID of the last used WAL file, for annotation purposes
 *	reason: human-readable explanation of why the timeline was switched
 *
 * Currently this is only used at the end recovery, and so there are no locking
 * considerations.	But we should be just as tense as XLogFileInit to avoid
 * emplacing a bogus file.
 */
void
writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI,
					 TimeLineID endTLI, XLogSegNo endLogSegNo, char *reason)
{
	char		path[MAXPGPATH];
	char		tmppath[MAXPGPATH];
	char		histfname[MAXFNAMELEN];
	char		xlogfname[MAXFNAMELEN];
	char		buffer[BLCKSZ];
	int			srcfd;
	int			fd;
	int			nbytes;

	Assert(newTLI > parentTLI); /* else bad selection of newTLI */

	/*
	 * Write into a temp file name.
	 */
	snprintf(tmppath, MAXPGPATH, XLOGDIR "/xlogtemp.%d", (int) getpid());

	unlink(tmppath);

	/* do not use get_sync_bit() here --- want to fsync only at end of fill */
	fd = OpenTransientFile(tmppath, O_RDWR | O_CREAT | O_EXCL,
						   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create file \"%s\": %m", tmppath)));

	/*
	 * If a history file exists for the parent, copy it verbatim
	 */
	if (InArchiveRecovery)
	{
		TLHistoryFileName(histfname, parentTLI);
		RestoreArchivedFile(path, histfname, "RECOVERYHISTORY", 0, false);
	}
	else
		TLHistoryFilePath(path, parentTLI);

	srcfd = OpenTransientFile(path, O_RDONLY, 0);
	if (srcfd < 0)
	{
		if (errno != ENOENT)
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not open file \"%s\": %m", path)));
		/* Not there, so assume parent has no parents */
	}
	else
	{
		for (;;)
		{
			errno = 0;
			nbytes = (int) read(srcfd, buffer, sizeof(buffer));
			if (nbytes < 0 || errno != 0)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not read file \"%s\": %m", path)));
			if (nbytes == 0)
				break;
			errno = 0;
			if ((int) write(fd, buffer, nbytes) != nbytes)
			{
				int			save_errno = errno;

				/*
				 * If we fail to make the file, delete it to release disk
				 * space
				 */
				unlink(tmppath);

				/*
				 * if write didn't set errno, assume problem is no disk space
				 */
				errno = save_errno ? save_errno : ENOSPC;

				ereport(ERROR,
						(errcode_for_file_access(),
					 errmsg("could not write to file \"%s\": %m", tmppath)));
			}
		}
		CloseTransientFile(srcfd);
	}

	/*
	 * Append one line with the details of this timeline split.
	 *
	 * If we did have a parent file, insert an extra newline just in case the
	 * parent file failed to end with one.
	 */
	XLogFileName(xlogfname, endTLI, endLogSegNo);

	snprintf(buffer, sizeof(buffer),
			 "%s%u\t%s\t%s\n",
			 (srcfd < 0) ? "" : "\n",
			 parentTLI,
			 xlogfname,
			 reason);

	nbytes = strlen(buffer);
	errno = 0;
	if ((int) write(fd, buffer, nbytes) != nbytes)
	{
		int			save_errno = errno;

		/*
		 * If we fail to make the file, delete it to release disk space
		 */
		unlink(tmppath);
		/* if write didn't set errno, assume problem is no disk space */
		errno = save_errno ? save_errno : ENOSPC;

		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not write to file \"%s\": %m", tmppath)));
	}

	if (pg_fsync(fd) != 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not fsync file \"%s\": %m", tmppath)));

	if (CloseTransientFile(fd))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not close file \"%s\": %m", tmppath)));


	/*
	 * Now move the completed history file into place with its final name.
	 */
	TLHistoryFilePath(path, newTLI);

	/*
	 * Prefer link() to rename() here just to be really sure that we don't
	 * overwrite an existing logfile.  However, there shouldn't be one, so
	 * rename() is an acceptable substitute except for the truly paranoid.
	 */
#if HAVE_WORKING_LINK
	if (link(tmppath, path) < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not link file \"%s\" to \"%s\": %m",
						tmppath, path)));
	unlink(tmppath);
#else
	if (rename(tmppath, path) < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not rename file \"%s\" to \"%s\": %m",
						tmppath, path)));
#endif

	/* The history file can be archived immediately. */
	TLHistoryFileName(histfname, newTLI);
	XLogArchiveNotify(histfname);
}