postgresql/src/backend/catalog/catalog.c

/*-------------------------------------------------------------------------
 *
 * catalog.c
 *		routines concerned with catalog naming conventions and other
 *		bits of hard-wired knowledge
 *
 *
 * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/catalog/catalog.c,v 1.69 2007/01/05 22:19:24 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include <fcntl.h>
#include <unistd.h>

#include "access/genam.h"
#include "access/transam.h"
#include "catalog/catalog.h"
#include "catalog/indexing.h"
#include "catalog/pg_auth_members.h"
#include "catalog/pg_authid.h"
#include "catalog/pg_database.h"
#include "catalog/pg_namespace.h"
#include "catalog/pg_pltemplate.h"
#include "catalog/pg_shdepend.h"
#include "catalog/pg_shdescription.h"
#include "catalog/pg_tablespace.h"
#include "catalog/toasting.h"
#include "miscadmin.h"
#include "storage/fd.h"
#include "utils/fmgroids.h"
#include "utils/relcache.h"


#define OIDCHARS	10			/* max chars printed by %u */


/*
 * relpath			- construct path to a relation's file
 *
 * Result is a palloc'd string.
 */
char *
relpath(RelFileNode rnode)
{
	int			pathlen;
	char	   *path;

	if (rnode.spcNode == GLOBALTABLESPACE_OID)
	{
		/* Shared system relations live in {datadir}/global */
		Assert(rnode.dbNode == 0);
		pathlen = 7 + OIDCHARS + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "global/%u",
				 rnode.relNode);
	}
	else if (rnode.spcNode == DEFAULTTABLESPACE_OID)
	{
		/* The default tablespace is {datadir}/base */
		pathlen = 5 + OIDCHARS + 1 + OIDCHARS + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "base/%u/%u",
				 rnode.dbNode, rnode.relNode);
	}
	else
	{
		/* All other tablespaces are accessed via symlinks */
		pathlen = 10 + OIDCHARS + 1 + OIDCHARS + 1 + OIDCHARS + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "pg_tblspc/%u/%u/%u",
				 rnode.spcNode, rnode.dbNode, rnode.relNode);
	}
	return path;
}

/*
 * GetDatabasePath			- construct path to a database dir
 *
 * Result is a palloc'd string.
 *
 * XXX this must agree with relpath()!
 */
char *
GetDatabasePath(Oid dbNode, Oid spcNode)
{
	int			pathlen;
	char	   *path;

	if (spcNode == GLOBALTABLESPACE_OID)
	{
		/* Shared system relations live in {datadir}/global */
		Assert(dbNode == 0);
		pathlen = 6 + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "global");
	}
	else if (spcNode == DEFAULTTABLESPACE_OID)
	{
		/* The default tablespace is {datadir}/base */
		pathlen = 5 + OIDCHARS + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "base/%u",
				 dbNode);
	}
	else
	{
		/* All other tablespaces are accessed via symlinks */
		pathlen = 10 + OIDCHARS + 1 + OIDCHARS + 1;
		path = (char *) palloc(pathlen);
		snprintf(path, pathlen, "pg_tblspc/%u/%u",
				 spcNode, dbNode);
	}
	return path;
}


/*
 * IsSystemRelation
 *		True iff the relation is a system catalog relation.
 *
 *		NB: TOAST relations are considered system relations by this test
 *		for compatibility with the old IsSystemRelationName function.
 *		This is appropriate in many places but not all.  Where it's not,
 *		also check IsToastRelation.
 *
 *		We now just test if the relation is in the system catalog namespace;
 *		so it's no longer necessary to forbid user relations from having
 *		names starting with pg_.
 */
bool
IsSystemRelation(Relation relation)
{
	return IsSystemNamespace(RelationGetNamespace(relation)) ||
		IsToastNamespace(RelationGetNamespace(relation));
}

/*
 * IsSystemClass
 *		Like the above, but takes a Form_pg_class as argument.
 *		Used when we do not want to open the relation and have to
 *		search pg_class directly.
 */
bool
IsSystemClass(Form_pg_class reltuple)
{
	Oid			relnamespace = reltuple->relnamespace;

	return IsSystemNamespace(relnamespace) ||
		IsToastNamespace(relnamespace);
}

/*
 * IsToastRelation
 *		True iff relation is a TOAST support relation (or index).
 */
bool
IsToastRelation(Relation relation)
{
	return IsToastNamespace(RelationGetNamespace(relation));
}

/*
 * IsToastClass
 *		Like the above, but takes a Form_pg_class as argument.
 *		Used when we do not want to open the relation and have to
 *		search pg_class directly.
 */
bool
IsToastClass(Form_pg_class reltuple)
{
	Oid			relnamespace = reltuple->relnamespace;

	return IsToastNamespace(relnamespace);
}

/*
 * IsSystemNamespace
 *		True iff namespace is pg_catalog.
 *
 * NOTE: the reason this isn't a macro is to avoid having to include
 * catalog/pg_namespace.h in a lot of places.
 */
bool
IsSystemNamespace(Oid namespaceId)
{
	return namespaceId == PG_CATALOG_NAMESPACE;
}

/*
 * IsToastNamespace
 *		True iff namespace is pg_toast.
 *
 * NOTE: the reason this isn't a macro is to avoid having to include
 * catalog/pg_namespace.h in a lot of places.
 */
bool
IsToastNamespace(Oid namespaceId)
{
	return namespaceId == PG_TOAST_NAMESPACE;
}


/*
 * IsReservedName
 *		True iff name starts with the pg_ prefix.
 *
 *		For some classes of objects, the prefix pg_ is reserved for
 *		system objects only.  As of 8.0, this is only true for
 *		schema and tablespace names.
 */
bool
IsReservedName(const char *name)
{
	/* ugly coding for speed */
	return (name[0] == 'p' &&
			name[1] == 'g' &&
			name[2] == '_');
}


/*
 * IsSharedRelation
 *		Given the OID of a relation, determine whether it's supposed to be
 *		shared across an entire database cluster.
 *
 * Hard-wiring this list is pretty grotty, but we really need it so that
 * we can compute the locktag for a relation (and then lock it) without
 * having already read its pg_class entry.	If we try to retrieve relisshared
 * from pg_class with no pre-existing lock, there is a race condition against
 * anyone who is concurrently committing a change to the pg_class entry:
 * since we read system catalog entries under SnapshotNow, it's possible
 * that both the old and new versions of the row are invalid at the instants
 * we scan them.  We fix this by insisting that updaters of a pg_class
 * row must hold exclusive lock on the corresponding rel, and that users
 * of a relation must hold at least AccessShareLock on the rel *before*
 * trying to open its relcache entry.  But to lock a rel, you have to
 * know if it's shared.  Fortunately, the set of shared relations is
 * fairly static, so a hand-maintained list of their OIDs isn't completely
 * impractical.
 */
bool
IsSharedRelation(Oid relationId)
{
	/* These are the shared catalogs (look for BKI_SHARED_RELATION) */
	if (relationId == AuthIdRelationId ||
		relationId == AuthMemRelationId ||
		relationId == DatabaseRelationId ||
		relationId == PLTemplateRelationId ||
		relationId == SharedDescriptionRelationId ||
		relationId == SharedDependRelationId ||
		relationId == TableSpaceRelationId)
		return true;
	/* These are their indexes (see indexing.h) */
	if (relationId == AuthIdRolnameIndexId ||
		relationId == AuthIdOidIndexId ||
		relationId == AuthMemRoleMemIndexId ||
		relationId == AuthMemMemRoleIndexId ||
		relationId == DatabaseNameIndexId ||
		relationId == DatabaseOidIndexId ||
		relationId == PLTemplateNameIndexId ||
		relationId == SharedDescriptionObjIndexId ||
		relationId == SharedDependDependerIndexId ||
		relationId == SharedDependReferenceIndexId ||
		relationId == TablespaceOidIndexId ||
		relationId == TablespaceNameIndexId)
		return true;
	/* These are their toast tables and toast indexes (see toasting.h) */
	if (relationId == PgAuthidToastTable ||
		relationId == PgAuthidToastIndex ||
		relationId == PgDatabaseToastTable ||
		relationId == PgDatabaseToastIndex ||
		relationId == PgShdescriptionToastTable ||
		relationId == PgShdescriptionToastIndex)
		return true;
	return false;
}


/*
 * GetNewOid
 *		Generate a new OID that is unique within the given relation.
 *
 * Caller must have a suitable lock on the relation.
 *
 * Uniqueness is promised only if the relation has a unique index on OID.
 * This is true for all system catalogs that have OIDs, but might not be
 * true for user tables.  Note that we are effectively assuming that the
 * table has a relatively small number of entries (much less than 2^32)
 * and there aren't very long runs of consecutive existing OIDs.  Again,
 * this is reasonable for system catalogs but less so for user tables.
 *
 * Since the OID is not immediately inserted into the table, there is a
 * race condition here; but a problem could occur only if someone else
 * managed to cycle through 2^32 OIDs and generate the same OID before we
 * finish inserting our row.  This seems unlikely to be a problem.	Note
 * that if we had to *commit* the row to end the race condition, the risk
 * would be rather higher; therefore we use SnapshotDirty in the test,
 * so that we will see uncommitted rows.
 */
Oid
GetNewOid(Relation relation)
{
	Oid			newOid;
	Oid			oidIndex;
	Relation	indexrel;

	/* If relation doesn't have OIDs at all, caller is confused */
	Assert(relation->rd_rel->relhasoids);

	/* In bootstrap mode, we don't have any indexes to use */
	if (IsBootstrapProcessingMode())
		return GetNewObjectId();

	/* The relcache will cache the identity of the OID index for us */
	oidIndex = RelationGetOidIndex(relation);

	/* If no OID index, just hand back the next OID counter value */
	if (!OidIsValid(oidIndex))
	{
		/*
		 * System catalogs that have OIDs should *always* have a unique OID
		 * index; we should only take this path for user tables. Give a
		 * warning if it looks like somebody forgot an index.
		 */
		if (IsSystemRelation(relation))
			elog(WARNING, "generating possibly-non-unique OID for \"%s\"",
				 RelationGetRelationName(relation));

		return GetNewObjectId();
	}

	/* Otherwise, use the index to find a nonconflicting OID */
	indexrel = index_open(oidIndex, AccessShareLock);
	newOid = GetNewOidWithIndex(relation, indexrel);
	index_close(indexrel, AccessShareLock);

	return newOid;
}

/*
 * GetNewOidWithIndex
 *		Guts of GetNewOid: use the supplied index
 *
 * This is exported separately because there are cases where we want to use
 * an index that will not be recognized by RelationGetOidIndex: TOAST tables
 * and pg_largeobject have indexes that are usable, but have multiple columns
 * and are on ordinary columns rather than a true OID column.  This code
 * will work anyway, so long as the OID is the index's first column.
 *
 * Caller must have a suitable lock on the relation.
 */
Oid
GetNewOidWithIndex(Relation relation, Relation indexrel)
{
	Oid			newOid;
	IndexScanDesc scan;
	ScanKeyData key;
	bool		collides;

	/* Generate new OIDs until we find one not in the table */
	do
	{
		newOid = GetNewObjectId();

		ScanKeyInit(&key,
					(AttrNumber) 1,
					BTEqualStrategyNumber, F_OIDEQ,
					ObjectIdGetDatum(newOid));

		/* see notes above about using SnapshotDirty */
		scan = index_beginscan(relation, indexrel,
							   SnapshotDirty, 1, &key);

		collides = HeapTupleIsValid(index_getnext(scan, ForwardScanDirection));

		index_endscan(scan);
	} while (collides);

	return newOid;
}

/*
 * GetNewRelFileNode
 *		Generate a new relfilenode number that is unique within the given
 *		tablespace.
 *
 * If the relfilenode will also be used as the relation's OID, pass the
 * opened pg_class catalog, and this routine will guarantee that the result
 * is also an unused OID within pg_class.  If the result is to be used only
 * as a relfilenode for an existing relation, pass NULL for pg_class.
 *
 * As with GetNewOid, there is some theoretical risk of a race condition,
 * but it doesn't seem worth worrying about.
 *
 * Note: we don't support using this in bootstrap mode.  All relations
 * created by bootstrap have preassigned OIDs, so there's no need.
 */
Oid
GetNewRelFileNode(Oid reltablespace, bool relisshared, Relation pg_class)
{
	RelFileNode rnode;
	char	   *rpath;
	int			fd;
	bool		collides;

	/* This should match RelationInitPhysicalAddr */
	rnode.spcNode = reltablespace ? reltablespace : MyDatabaseTableSpace;
	rnode.dbNode = relisshared ? InvalidOid : MyDatabaseId;

	do
	{
		/* Generate the OID */
		if (pg_class)
			rnode.relNode = GetNewOid(pg_class);
		else
			rnode.relNode = GetNewObjectId();

		/* Check for existing file of same name */
		rpath = relpath(rnode);
		fd = BasicOpenFile(rpath, O_RDONLY | PG_BINARY, 0);

		if (fd >= 0)
		{
			/* definite collision */
			close(fd);
			collides = true;
		}
		else
		{
			/*
			 * Here we have a little bit of a dilemma: if errno is something
			 * other than ENOENT, should we declare a collision and loop? In
			 * particular one might think this advisable for, say, EPERM.
			 * However there really shouldn't be any unreadable files in a
			 * tablespace directory, and if the EPERM is actually complaining
			 * that we can't read the directory itself, we'd be in an infinite
			 * loop.  In practice it seems best to go ahead regardless of the
			 * errno.  If there is a colliding file we will get an smgr
			 * failure when we attempt to create the new relation file.
			 */
			collides = false;
		}

		pfree(rpath);
	} while (collides);

	return rnode.relNode;
}