On Tue, 26 Apr 2005, Alvaro Herrera wrote:
You forgot the attachment?
Damn. It happens time after time...
- Heikki
Index: doc/src/sgml/maintenance.sgml
===================================================================
RCS file: /projects/cvsroot/pgsql/doc/src/sgml/maintenance.sgml,v
retrieving revision 1.41
diff -c -r1.41 maintenance.sgml
*** doc/src/sgml/maintenance.sgml 20 Feb 2005 02:21:26 -0000 1.41
--- doc/src/sgml/maintenance.sgml 26 Apr 2005 22:02:22 -0000
***************
*** 474,479 ****
--- 474,496 ----
</para>
</sect1>
+ <sect1 id="cleanup-after-crash">
+ <title>Cleanup after crash</title>
+
+ <indexterm zone="cleanup-after-crash">
+ <primary>stale file</primary>
+ </indexterm>
+
+ <para>
+ <productname>PostgreSQL</productname> recovers automatically after crash
+ using the write-ahead log (see <xref linkend="wal">) and no manual
+ operations are normally needed. However, if there was a transaction
running
+ when the crash occured that created or dropped a relation, the
+ transaction might have left a stale file in the data directory. If this
+ happens, you will get a notice in the log file stating which files can be
+ deleted.
+ </para>
+ </sect1>
<sect1 id="logfile-maintenance">
<title>Log File Maintenance</title>
Index: src/backend/access/transam/xlog.c
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/access/transam/xlog.c,v
retrieving revision 1.188
diff -c -r1.188 xlog.c
*** src/backend/access/transam/xlog.c 23 Apr 2005 18:49:54 -0000 1.188
--- src/backend/access/transam/xlog.c 26 Apr 2005 22:02:22 -0000
***************
*** 42,47 ****
--- 42,48 ----
#include "utils/builtins.h"
#include "utils/guc.h"
#include "utils/relcache.h"
+ #include "utils/cleanup.h"
/*
***************
*** 4520,4525 ****
--- 4521,4528 ----
CreateCheckPoint(true, true);
+ CleanupStaleRelFiles();
+
/*
* Close down recovery environment
*/
Index: src/backend/catalog/catalog.c
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/catalog/catalog.c,v
retrieving revision 1.59
diff -c -r1.59 catalog.c
*** src/backend/catalog/catalog.c 14 Apr 2005 20:03:23 -0000 1.59
--- src/backend/catalog/catalog.c 26 Apr 2005 22:02:22 -0000
***************
*** 106,111 ****
--- 106,144 ----
return path;
}
+ /*
+ * GetTablespacePath - construct path to a tablespace symbolic link
+ *
+ * Result is a palloc'd string.
+ *
+ * XXX this must agree with relpath and GetDatabasePath!
+ */
+ char *
+ GetTablespacePath(Oid spcNode)
+ {
+ int pathlen;
+ char *path;
+
+ Assert(spcNode != GLOBALTABLESPACE_OID);
+
+ if (spcNode == DEFAULTTABLESPACE_OID)
+ {
+ /* The default tablespace is {datadir}/base */
+ pathlen = strlen(DataDir) + 5 + 1;
+ path = (char *) palloc(pathlen);
+ snprintf(path, pathlen, "%s/base",
+ DataDir);
+ }
+ else
+ {
+ /* All other tablespaces have symlinks in pg_tblspc */
+ pathlen = strlen(DataDir) + 11 + OIDCHARS + 1;
+ path = (char *) palloc(pathlen);
+ snprintf(path, pathlen, "%s/pg_tblspc/%u",
+ DataDir, spcNode);
+ }
+ return path;
+ }
/*
* IsSystemRelation
Index: src/backend/commands/tablespace.c
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/commands/tablespace.c,v
retrieving revision 1.17
diff -c -r1.17 tablespace.c
*** src/backend/commands/tablespace.c 14 Apr 2005 20:03:24 -0000 1.17
--- src/backend/commands/tablespace.c 26 Apr 2005 22:02:23 -0000
***************
*** 341,348 ****
/*
* All seems well, create the symlink
*/
! linkloc = (char *) palloc(strlen(DataDir) + 11 + 10 + 1);
! sprintf(linkloc, "%s/pg_tblspc/%u", DataDir, tablespaceoid);
if (symlink(location, linkloc) < 0)
ereport(ERROR,
--- 341,347 ----
/*
* All seems well, create the symlink
*/
! linkloc = GetTablespacePath(tablespaceoid);
if (symlink(location, linkloc) < 0)
ereport(ERROR,
***************
*** 495,502 ****
char *subfile;
struct stat st;
! location = (char *) palloc(strlen(DataDir) + 11 + 10 + 1);
! sprintf(location, "%s/pg_tblspc/%u", DataDir, tablespaceoid);
/*
* Check if the tablespace still contains any files. We try to rmdir
--- 494,500 ----
char *subfile;
struct stat st;
! location = GetTablespacePath(tablespaceoid);
/*
* Check if the tablespace still contains any files. We try to rmdir
***************
*** 1036,1043 ****
set_short_version(location);
/* Create the symlink if not already present */
! linkloc = (char *) palloc(strlen(DataDir) + 11 + 10 + 1);
! sprintf(linkloc, "%s/pg_tblspc/%u", DataDir, xlrec->ts_id);
if (symlink(location, linkloc) < 0)
{
--- 1034,1040 ----
set_short_version(location);
/* Create the symlink if not already present */
! linkloc = GetTablespacePath(xlrec->ts_id);
if (symlink(location, linkloc) < 0)
{
Index: src/backend/utils/adt/misc.c
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/utils/adt/misc.c,v
retrieving revision 1.40
diff -c -r1.40 misc.c
*** src/backend/utils/adt/misc.c 31 Dec 2004 22:01:22 -0000 1.40
--- src/backend/utils/adt/misc.c 26 Apr 2005 22:02:23 -0000
***************
*** 26,31 ****
--- 26,32 ----
#include "funcapi.h"
#include "catalog/pg_type.h"
#include "catalog/pg_tablespace.h"
+ #include "catalog/catalog.h"
#define atooid(x) ((Oid) strtoul((x), NULL, 10))
***************
*** 144,154 ****
fctx = palloc(sizeof(ts_db_fctx));
- /*
- * size = path length + tablespace dirname length + 2 dir sep
- * chars + oid + terminator
- */
- fctx->location = (char *) palloc(strlen(DataDir) + 11 + 10 + 1);
if (tablespaceOid == GLOBALTABLESPACE_OID)
{
fctx->dirdesc = NULL;
--- 145,150 ----
***************
*** 157,168 ****
}
else
{
! if (tablespaceOid == DEFAULTTABLESPACE_OID)
! sprintf(fctx->location, "%s/base", DataDir);
! else
! sprintf(fctx->location, "%s/pg_tblspc/%u",
DataDir,
! tablespaceOid);
!
fctx->dirdesc = AllocateDir(fctx->location);
if (!fctx->dirdesc)
--- 153,159 ----
}
else
{
! fctx->location = GetTablespacePath(tablespaceOid);
fctx->dirdesc = AllocateDir(fctx->location);
if (!fctx->dirdesc)
Index: src/backend/utils/init/Makefile
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/utils/init/Makefile,v
retrieving revision 1.18
diff -c -r1.18 Makefile
*** src/backend/utils/init/Makefile 20 Feb 2005 02:22:00 -0000 1.18
--- src/backend/utils/init/Makefile 26 Apr 2005 22:02:23 -0000
***************
*** 12,18 ****
top_builddir = ../../../..
include $(top_builddir)/src/Makefile.global
! OBJS = flatfiles.o globals.o miscinit.o postinit.o
all: SUBSYS.o
--- 12,18 ----
top_builddir = ../../../..
include $(top_builddir)/src/Makefile.global
! OBJS = flatfiles.o globals.o miscinit.o postinit.o cleanup.o
all: SUBSYS.o
Index: src/backend/utils/init/cleanup.c
===================================================================
RCS file: src/backend/utils/init/cleanup.c
diff -N src/backend/utils/init/cleanup.c
*** /dev/null 1 Jan 1970 00:00:00 -0000
--- src/backend/utils/init/cleanup.c 26 Apr 2005 22:02:23 -0000
***************
*** 0 ****
--- 1,209 ----
+ /*-------------------------------------------------------------------------
+ *
+ * cleanup.c
+ * support to clean up stale relation files on crash recovery
+ *
+ * If a backend crashes while in a transaction that has created or
+ * deleted a relfilenode, a stale file can be left over in the data
+ * directory. This file contains routines to clean up those stale
+ * files on recovery.
+ *
+ * $PostgreSQL$
+ *
+ *-------------------------------------------------------------------------
+ */
+ #include "postgres.h"
+
+ #include "storage/fd.h"
+
+ #include "utils/cleanup.h"
+ #include "miscadmin.h"
+ #include "catalog/pg_tablespace.h"
+ #include "catalog/catalog.h"
+ #include "access/skey.h"
+ #include "utils/fmgroids.h"
+ #include "access/relscan.h"
+ #include "access/heapam.h"
+ #include "utils/resowner.h"
+
+ static void CleanupStaleRelFilesFrom(Oid tablespaceoid, Oid dboid);
+ static void CleanupStaleRelFilesFromTablespace(Oid tablespaceoid);
+
+ /* Like AllocateDir, but ereports on failure */
+ static DIR *
+ AllocateDirChecked(char *path)
+ {
+ DIR *dirdesc = AllocateDir(path);
+ if (dirdesc == NULL)
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not open directory \"%s\": %m",
+ path)));
+ return dirdesc;
+ }
+
+ /*
+ * Scan through all tablespaces for relations left over
+ * by aborted transactions.
+ *
+ * For example, if a transaction issues
+ * BEGIN; CREATE TABLE foobar ();
+ * and then the backend crashes, the file is left in the
+ * tablespace until CleanupStaleRelFiles deletes it.
+ */
+ void
+ CleanupStaleRelFiles(void)
+ {
+ DIR *dirdesc;
+ struct dirent *de;
+ char *path;
+ int pathlen;
+
+ pathlen = strlen(DataDir) + 11 + 1;
+ path = (char *) palloc(pathlen);
+ snprintf(path, pathlen, "%s/pg_tblspc/", DataDir);
+ dirdesc = AllocateDirChecked(path);
+ while ((de = readdir(dirdesc)) != NULL)
+ {
+ char *invalid;
+ Oid tablespaceoid;
+
+ /* Check that the directory name looks like valid tablespace
link. */
+ tablespaceoid = (Oid) strtol(de->d_name, &invalid, 10);
+ if(invalid[0] == '\0')
+ CleanupStaleRelFilesFromTablespace(tablespaceoid);
+ }
+ pfree(path);
+
+ CleanupStaleRelFilesFromTablespace(DEFAULTTABLESPACE_OID);
+ }
+
+ /* Scan a specific tablespace for stale relations */
+ static void
+ CleanupStaleRelFilesFromTablespace(Oid tablespaceoid)
+ {
+ DIR *dirdesc;
+ struct dirent *de;
+ char *path;
+
+ path = GetTablespacePath(tablespaceoid);
+
+ dirdesc = AllocateDirChecked(path);
+ while ((de = readdir(dirdesc)) != NULL)
+ {
+ char *invalid;
+ Oid dboid;
+
+ dboid = (Oid) strtol(de->d_name, &invalid, 10);
+ if(invalid[0] == '\0')
+ CleanupStaleRelFilesFrom(tablespaceoid, dboid);
+ }
+ pfree(path);
+ }
+
+ /* Scan a specific database in a specific tablespace for stale relations.
+ *
+ * First, pg_class for the database is opened, and the relfilenodes of all
+ * relations mentioned there are stored in a hash table.
+ *
+ * Then the directory is scanned. Every file in the directory that's not
+ * found in pg_class (the hash table) is logged.
+ */
+ static void
+ CleanupStaleRelFilesFrom(Oid tablespaceoid, Oid dboid)
+ {
+ DIR *dirdesc;
+ struct dirent *de;
+ HASHCTL hashctl;
+ HTAB *relfilenodeHash;
+ MemoryContext mcxt;
+ RelFileNode rnode;
+ char *path;
+
+ /* We create a private memory context so that we can easily deallocate
+ * the hash table and its contents
+ */
+ mcxt = AllocSetContextCreate(TopMemoryContext, "CleanupStaleRelFiles",
+
ALLOCSET_DEFAULT_MINSIZE,
+
ALLOCSET_DEFAULT_INITSIZE,
+
ALLOCSET_DEFAULT_MAXSIZE);
+
+ hashctl.hash = tag_hash;
+ /* The entry contents is not used for anything, we just check
+ * if an oid is in the hash table or not. */
+ hashctl.keysize = sizeof(Oid);
+ hashctl.entrysize = 1;
+ hashctl.hcxt = mcxt;
+ relfilenodeHash = hash_create("relfilenodeHash", 100, &hashctl,
+ HASH_FUNCTION
+ | HASH_ELEM |
HASH_CONTEXT);
+
+ /* Read all relfilenodes from pg_class into the hash table */
+ {
+ ResourceOwner owner;
+ ResourceOwner oldowner;
+ Relation rel;
+ HeapScanDesc scan;
+ HeapTuple tuple;
+
+ /* Need a resowner to keep the heapam and buffer code happy */
+ owner = ResourceOwnerCreate(NULL, "CleanupStaleRelFiles");
+ oldowner = CurrentResourceOwner;
+ CurrentResourceOwner = owner;
+
+ rnode.spcNode = tablespaceoid;
+ rnode.dbNode = dboid;
+ rnode.relNode = RelationRelationId;
+ rel = XLogOpenRelation(true, 0 , rnode);
+
+ scan = heap_beginscan(rel, SnapshotNow, 0, NULL);
+ while ((tuple = heap_getnext(scan, ForwardScanDirection)) !=
NULL)
+ {
+ Form_pg_class classform = (Form_pg_class)
GETSTRUCT(tuple);
+
+ hash_search(relfilenodeHash, &classform->relfilenode,
+ HASH_ENTER, NULL);
+ }
+ heap_endscan(scan);
+
+ XLogCloseRelation(rnode);
+ CurrentResourceOwner = oldowner;
+ ResourceOwnerDelete(owner);
+ }
+
+ /* Scan the directory */
+ path = GetDatabasePath(dboid, tablespaceoid);
+
+ dirdesc = AllocateDirChecked(path);
+ while ((de = readdir(dirdesc)) != NULL)
+ {
+ char *invalid;
+ Oid relfilenode;
+
+ relfilenode = strtol(de->d_name, &invalid, 10);
+ if(invalid[0] == '\0')
+ {
+ /* Filename was a valid number, check if pg_class knows
+ about it */
+ if(hash_search(relfilenodeHash, &relfilenode,
+ HASH_FIND, NULL) == NULL)
+ {
+ char *filepath;
+ rnode.spcNode = tablespaceoid;
+ rnode.dbNode = dboid;
+ rnode.relNode = relfilenode;
+
+ filepath = relpath(rnode);
+
+ ereport(NOTICE,
+ (errcode_for_file_access(),
+ errmsg("The relation file
\"%s\" is stale and can be safely deleted",
+ filepath)));
+ pfree(filepath);
+ }
+ }
+ }
+ pfree(path);
+ hash_destroy(relfilenodeHash);
+ MemoryContextDelete(mcxt);
+ }
Index: src/include/catalog/catalog.h
===================================================================
RCS file: /projects/cvsroot/pgsql/src/include/catalog/catalog.h,v
retrieving revision 1.30
diff -c -r1.30 catalog.h
*** src/include/catalog/catalog.h 31 Dec 2004 22:03:24 -0000 1.30
--- src/include/catalog/catalog.h 26 Apr 2005 22:02:23 -0000
***************
*** 19,24 ****
--- 19,25 ----
extern char *relpath(RelFileNode rnode);
extern char *GetDatabasePath(Oid dbNode, Oid spcNode);
+ extern char *GetTablespacePath(Oid spcNode);
extern bool IsSystemRelation(Relation relation);
extern bool IsToastRelation(Relation relation);
---------------------------(end of broadcast)---------------------------
TIP 6: Have you searched our list archives?
http://archives.postgresql.org
