tablespace.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*-------------------------------------------------------------------------
 *
 * tablespace.c
 *	  Commands to manipulate table spaces
 *
 * Tablespaces in PostgreSQL are designed to allow users to determine
 * where the data file(s) for a given database object reside on the file
 * system.
 *
 * A tablespace represents a directory on the file system. At tablespace
 * creation time, the directory must be empty. To simplify things and
 * remove the possibility of having file name conflicts, we isolate
 * files within a tablespace into database-specific subdirectories.
 *
 * To support file access via the information given in RelFileNode, we
 * maintain a symbolic-link map in $PGDATA/pg_tblspc. The symlinks are
 * named by tablespace OIDs and point to the actual tablespace directories.
 * Thus the full path to an arbitrary file is
 *			$PGDATA/pg_tblspc/spcoid/dboid/relfilenode
 *
 * There are two tablespaces created at initdb time: pg_global (for shared
 * tables) and pg_default (for everything else).  For backwards compatibility
 * and to remain functional on platforms without symlinks, these tablespaces
 * are accessed specially: they are respectively
 *			$PGDATA/global/relfilenode
 *			$PGDATA/base/dboid/relfilenode
 *
 * To allow CREATE DATABASE to give a new database a default tablespace
 * that's different from the template database's default, we make the
 * provision that a zero in pg_class.reltablespace means the database's
 * default tablespace.	Without this, CREATE DATABASE would have to go in
 * and munge the system catalogs of the new database.
 *
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/commands/tablespace.c,v 1.28.2.2 2006/03/29 15:15:50 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <unistd.h>
#include <dirent.h>
#include <sys/types.h>
#include <sys/stat.h>

#include "access/heapam.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/indexing.h"
#include "catalog/pg_namespace.h"
#include "catalog/pg_tablespace.h"
#include "commands/tablespace.h"
#include "miscadmin.h"
#include "storage/fd.h"
#include "storage/smgr.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/fmgroids.h"
#include "utils/guc.h"
#include "utils/lsyscache.h"
#include "utils/syscache.h"


/* GUC variable */
char	   *default_tablespace = NULL;


static bool remove_tablespace_directories(Oid tablespaceoid, bool redo);
static void set_short_version(const char *path);


/*
 * Each database using a table space is isolated into its own name space
 * by a subdirectory named for the database OID.  On first creation of an
 * object in the tablespace, create the subdirectory.  If the subdirectory
 * already exists, just fall through quietly.
 *
 * isRedo indicates that we are creating an object during WAL replay.
 * In this case we will cope with the possibility of the tablespace
 * directory not being there either --- this could happen if we are
 * replaying an operation on a table in a subsequently-dropped tablespace.
 * We handle this by making a directory in the place where the tablespace
 * symlink would normally be.  This isn't an exact replay of course, but
 * it's the best we can do given the available information.
 *
 * If tablespaces are not supported, you might think this could be a no-op,
 * but you'd be wrong: we still need it in case we have to re-create a
 * database subdirectory (of $PGDATA/base) during WAL replay.
 */
void
TablespaceCreateDbspace(Oid spcNode, Oid dbNode, bool isRedo)
{
	struct stat st;
	char	   *dir;

	/*
	 * The global tablespace doesn't have per-database subdirectories, so
	 * nothing to do for it.
	 */
	if (spcNode == GLOBALTABLESPACE_OID)
		return;

	Assert(OidIsValid(spcNode));
	Assert(OidIsValid(dbNode));

	dir = GetDatabasePath(dbNode, spcNode);

	if (stat(dir, &st) < 0)
	{
		if (errno == ENOENT)
		{
			/*
			 * Acquire TablespaceCreateLock to ensure that no DROP TABLESPACE
			 * or TablespaceCreateDbspace is running concurrently.
			 */
			LWLockAcquire(TablespaceCreateLock, LW_EXCLUSIVE);

			/*
			 * Recheck to see if someone created the directory while we were
			 * waiting for lock.
			 */
			if (stat(dir, &st) == 0 && S_ISDIR(st.st_mode))
			{
				/* need not do anything */
			}
			else
			{
				/* OK, go for it */
				if (mkdir(dir, S_IRWXU) < 0)
				{
					char	   *parentdir;

					if (errno != ENOENT || !isRedo)
						ereport(ERROR,
								(errcode_for_file_access(),
							  errmsg("could not create directory \"%s\": %m",
									 dir)));
					/* Try to make parent directory too */
					parentdir = pstrdup(dir);
					get_parent_directory(parentdir);
					if (mkdir(parentdir, S_IRWXU) < 0)
						ereport(ERROR,
								(errcode_for_file_access(),
							  errmsg("could not create directory \"%s\": %m",
									 parentdir)));
					pfree(parentdir);
					if (mkdir(dir, S_IRWXU) < 0)
						ereport(ERROR,
								(errcode_for_file_access(),
							  errmsg("could not create directory \"%s\": %m",
									 dir)));
				}
			}

			LWLockRelease(TablespaceCreateLock);
		}
		else
		{
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not stat directory \"%s\": %m", dir)));
		}
	}
	else
	{
		/* be paranoid */
		if (!S_ISDIR(st.st_mode))
			ereport(ERROR,
					(errcode(ERRCODE_WRONG_OBJECT_TYPE),
					 errmsg("\"%s\" exists but is not a directory",
							dir)));
	}

	pfree(dir);
}

/*
 * Create a table space
 *
 * Only superusers can create a tablespace. This seems a reasonable restriction
 * since we're determining the system layout and, anyway, we probably have
 * root if we're doing this kind of activity
 */
void
CreateTableSpace(CreateTableSpaceStmt *stmt)
{
#ifdef HAVE_SYMLINK
	Relation	rel;
	Datum		values[Natts_pg_tablespace];
	char		nulls[Natts_pg_tablespace];
	HeapTuple	tuple;
	Oid			tablespaceoid;
	char	   *location;
	char	   *linkloc;
	Oid			ownerId;

	/* validate */

	/* don't call this in a transaction block */
	PreventTransactionChain((void *) stmt, "CREATE TABLESPACE");

	/* Must be super user */
	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("permission denied to create tablespace \"%s\"",
						stmt->tablespacename),
				 errhint("Must be superuser to create a tablespace.")));

	/* However, the eventual owner of the tablespace need not be */
	if (stmt->owner)
		ownerId = get_roleid_checked(stmt->owner);
	else
		ownerId = GetUserId();

	/* Unix-ify the offered path, and strip any trailing slashes */
	location = pstrdup(stmt->location);
	canonicalize_path(location);

	/* disallow quotes, else CREATE DATABASE would be at risk */
	if (strchr(location, '\''))
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_NAME),
			   errmsg("tablespace location may not contain single quotes")));

	/*
	 * Allowing relative paths seems risky
	 *
	 * this also helps us ensure that location is not empty or whitespace
	 */
	if (!is_absolute_path(location))
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
				 errmsg("tablespace location must be an absolute path")));

	/*
	 * Check that location isn't too long. Remember that we're going to append
	 * '/<dboid>/<relid>.<nnn>'  (XXX but do we ever form the whole path
	 * explicitly?	This may be overly conservative.)
	 */
	if (strlen(location) >= (MAXPGPATH - 1 - 10 - 1 - 10 - 1 - 10))
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
				 errmsg("tablespace location \"%s\" is too long",
						location)));

	/*
	 * Disallow creation of tablespaces named "pg_xxx"; we reserve this
	 * namespace for system purposes.
	 */
	if (!allowSystemTableMods && IsReservedName(stmt->tablespacename))
		ereport(ERROR,
				(errcode(ERRCODE_RESERVED_NAME),
				 errmsg("unacceptable tablespace name \"%s\"",
						stmt->tablespacename),
		errdetail("The prefix \"pg_\" is reserved for system tablespaces.")));

	/*
	 * Check that there is no other tablespace by this name.  (The unique
	 * index would catch this anyway, but might as well give a friendlier
	 * message.)
	 */
	if (OidIsValid(get_tablespace_oid(stmt->tablespacename)))
		ereport(ERROR,
				(errcode(ERRCODE_DUPLICATE_OBJECT),
				 errmsg("tablespace \"%s\" already exists",
						stmt->tablespacename)));

	/*
	 * Insert tuple into pg_tablespace.  The purpose of doing this first is to
	 * lock the proposed tablename against other would-be creators. The
	 * insertion will roll back if we find problems below.
	 */
	rel = heap_open(TableSpaceRelationId, RowExclusiveLock);

	MemSet(nulls, ' ', Natts_pg_tablespace);

	values[Anum_pg_tablespace_spcname - 1] =
		DirectFunctionCall1(namein, CStringGetDatum(stmt->tablespacename));
	values[Anum_pg_tablespace_spcowner - 1] =
		ObjectIdGetDatum(ownerId);
	values[Anum_pg_tablespace_spclocation - 1] =
		DirectFunctionCall1(textin, CStringGetDatum(location));
	nulls[Anum_pg_tablespace_spcacl - 1] = 'n';

	tuple = heap_formtuple(rel->rd_att, values, nulls);

	tablespaceoid = simple_heap_insert(rel, tuple);

	CatalogUpdateIndexes(rel, tuple);

	heap_freetuple(tuple);

	/* Record dependency on owner */
	recordDependencyOnOwner(TableSpaceRelationId, tablespaceoid, ownerId);

	/*
	 * Attempt to coerce target directory to safe permissions.	If this fails,
	 * it doesn't exist or has the wrong owner.
	 */
	if (chmod(location, 0700) != 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not set permissions on directory \"%s\": %m",
						location)));

	/*
	 * Check the target directory is empty.
	 */
	if (!directory_is_empty(location))
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("directory \"%s\" is not empty",
						location)));

	/*
	 * Create the PG_VERSION file in the target directory.	This has several
	 * purposes: to make sure we can write in the directory, to prevent
	 * someone from creating another tablespace pointing at the same directory
	 * (the emptiness check above will fail), and to label tablespace
	 * directories by PG version.
	 */
	set_short_version(location);

	/*
	 * All seems well, create the symlink
	 */
	linkloc = (char *) palloc(10 + 10 + 1);
	sprintf(linkloc, "pg_tblspc/%u", tablespaceoid);

	if (symlink(location, linkloc) < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create symbolic link \"%s\": %m",
						linkloc)));

	/* Record the filesystem change in XLOG */
	{
		xl_tblspc_create_rec xlrec;
		XLogRecData rdata[2];

		xlrec.ts_id = tablespaceoid;
		rdata[0].data = (char *) &xlrec;
		rdata[0].len = offsetof(xl_tblspc_create_rec, ts_path);
		rdata[0].buffer = InvalidBuffer;
		rdata[0].next = &(rdata[1]);

		rdata[1].data = (char *) location;
		rdata[1].len = strlen(location) + 1;
		rdata[1].buffer = InvalidBuffer;
		rdata[1].next = NULL;

		(void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_CREATE, rdata);
	}

	pfree(linkloc);
	pfree(location);

	/* We keep the lock on pg_tablespace until commit */
	heap_close(rel, NoLock);
#else							/* !HAVE_SYMLINK */
	ereport(ERROR,
			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
			 errmsg("tablespaces are not supported on this platform")));
#endif   /* HAVE_SYMLINK */
}

/*
 * Drop a table space
 *
 * Be careful to check that the tablespace is empty.
 */
void
DropTableSpace(DropTableSpaceStmt *stmt)
{
#ifdef HAVE_SYMLINK
	char	   *tablespacename = stmt->tablespacename;
	HeapScanDesc scandesc;
	Relation	rel;
	HeapTuple	tuple;
	ScanKeyData entry[1];
	Oid			tablespaceoid;

	/* don't call this in a transaction block */
	PreventTransactionChain((void *) stmt, "DROP TABLESPACE");

	/*
	 * Find the target tuple
	 */
	rel = heap_open(TableSpaceRelationId, RowExclusiveLock);

	ScanKeyInit(&entry[0],
				Anum_pg_tablespace_spcname,
				BTEqualStrategyNumber, F_NAMEEQ,
				CStringGetDatum(tablespacename));
	scandesc = heap_beginscan(rel, SnapshotNow, 1, entry);
	tuple = heap_getnext(scandesc, ForwardScanDirection);

	if (!HeapTupleIsValid(tuple))
		ereport(ERROR,
				(errcode(ERRCODE_UNDEFINED_OBJECT),
				 errmsg("tablespace \"%s\" does not exist",
						tablespacename)));

	tablespaceoid = HeapTupleGetOid(tuple);

	/* Must be tablespace owner */
	if (!pg_tablespace_ownercheck(tablespaceoid, GetUserId()))
		aclcheck_error(ACLCHECK_NOT_OWNER, ACL_KIND_TABLESPACE,
					   tablespacename);

	/* Disallow drop of the standard tablespaces, even by superuser */
	if (tablespaceoid == GLOBALTABLESPACE_OID ||
		tablespaceoid == DEFAULTTABLESPACE_OID)
		aclcheck_error(ACLCHECK_NO_PRIV, ACL_KIND_TABLESPACE,
					   tablespacename);

	/*
	 * Remove the pg_tablespace tuple (this will roll back if we fail below)
	 */
	simple_heap_delete(rel, &tuple->t_self);

	heap_endscan(scandesc);

	/*
	 * Remove dependency on owner.
	 */
	deleteSharedDependencyRecordsFor(TableSpaceRelationId, tablespaceoid);

	/*
	 * Acquire TablespaceCreateLock to ensure that no TablespaceCreateDbspace
	 * is running concurrently.
	 */
	LWLockAcquire(TablespaceCreateLock, LW_EXCLUSIVE);

	/*
	 * Try to remove the physical infrastructure
	 */
	if (!remove_tablespace_directories(tablespaceoid, false))
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("tablespace \"%s\" is not empty",
						tablespacename)));

	/* Record the filesystem change in XLOG */
	{
		xl_tblspc_drop_rec xlrec;
		XLogRecData rdata[1];

		xlrec.ts_id = tablespaceoid;
		rdata[0].data = (char *) &xlrec;
		rdata[0].len = sizeof(xl_tblspc_drop_rec);
		rdata[0].buffer = InvalidBuffer;
		rdata[0].next = NULL;

		(void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_DROP, rdata);
	}

	/*
	 * Allow TablespaceCreateDbspace again.
	 */
	LWLockRelease(TablespaceCreateLock);

	/* We keep the lock on pg_tablespace until commit */
	heap_close(rel, NoLock);
#else							/* !HAVE_SYMLINK */
	ereport(ERROR,
			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
			 errmsg("tablespaces are not supported on this platform")));
#endif   /* HAVE_SYMLINK */
}

/*
 * remove_tablespace_directories: attempt to remove filesystem infrastructure
 *
 * Returns TRUE if successful, FALSE if some subdirectory is not empty
 *
 * redo indicates we are redoing a drop from XLOG; okay if nothing there
 */
static bool
remove_tablespace_directories(Oid tablespaceoid, bool redo)
{
	char	   *location;
	DIR		   *dirdesc;
	struct dirent *de;
	char	   *subfile;
	struct stat st;

	location = (char *) palloc(10 + 10 + 1);
	sprintf(location, "pg_tblspc/%u", tablespaceoid);

	/*
	 * Check if the tablespace still contains any files.  We try to rmdir each
	 * per-database directory we find in it.  rmdir failure implies there are
	 * still files in that subdirectory, so give up.  (We do not have to worry
	 * about undoing any already completed rmdirs, since the next attempt to
	 * use the tablespace from that database will simply recreate the
	 * subdirectory via TablespaceCreateDbspace.)
	 *
	 * Since we hold TablespaceCreateLock, no one else should be creating any
	 * fresh subdirectories in parallel. It is possible that new files are
	 * being created within subdirectories, though, so the rmdir call could
	 * fail.  Worst consequence is a less friendly error message.
	 */
	dirdesc = AllocateDir(location);
	if (dirdesc == NULL)
	{
		if (redo && errno == ENOENT)
		{
			pfree(location);
			return true;
		}
		/* else let ReadDir report the error */
	}

	while ((de = ReadDir(dirdesc, location)) != NULL)
	{
		/* Note we ignore PG_VERSION for the nonce */
		if (strcmp(de->d_name, ".") == 0 ||
			strcmp(de->d_name, "..") == 0 ||
			strcmp(de->d_name, "PG_VERSION") == 0)
			continue;

		subfile = palloc(strlen(location) + 1 + strlen(de->d_name) + 1);
		sprintf(subfile, "%s/%s", location, de->d_name);