Add code to apply some simple sanity checks to the header fields of a

page when it's read in, per pghackers discussion around 17-Feb.  Add a
GUC variable zero_damaged_pages that causes the response to be a WARNING
followed by zeroing the page, rather than the normal ERROR; this is per
Hiroshi's suggestion that there needs to be a way to get at the data
in the rest of the table.

src/backend/storage/buffer/bufmgr.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/storage/buffer/bufmgr.c,v 1.134 2003/02/13 05:35:11 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/storage/buffer/bufmgr.c,v 1.135 2003/03/28 20:17:13 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -49,6 +49,7 @@
 #include "miscadmin.h"
 #include "storage/buf_internals.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
 #include "storage/proc.h"
 #include "storage/smgr.h"
 #include "utils/relcache.h"
@@ -59,6 +60,10 @@
 	(*((XLogRecPtr*) MAKE_PTR((bufHdr)->data)))
 
 
+/* GUC variable */
+bool	zero_damaged_pages = false;
+
+
 static void WaitIO(BufferDesc *buf);
 static void StartBufferIO(BufferDesc *buf, bool forInput);
 static void TerminateBufferIO(BufferDesc *buf);
@@ -217,6 +222,20 @@ ReadBufferInternal(Relation reln, BlockNumber blockNum,
 	{
 		status = smgrread(DEFAULT_SMGR, reln, blockNum,
 						  (char *) MAKE_PTR(bufHdr->data));
+		/* check for garbage data */
+		if (status == SM_SUCCESS &&
+			!PageHeaderIsValid((PageHeader) MAKE_PTR(bufHdr->data)))
+		{
+			if (zero_damaged_pages)
+			{
+				elog(WARNING, "Invalid page header in block %u of %s; zeroing out page",
+					 blockNum, RelationGetRelationName(reln));
+				MemSet((char *) MAKE_PTR(bufHdr->data), 0, BLCKSZ);
+			}
+			else
+				elog(ERROR, "Invalid page header in block %u of %s",
+					 blockNum, RelationGetRelationName(reln));
+		}
 	}
 
 	if (isLocalBuf)

src/backend/storage/page/bufpage.c

@@ -8,14 +8,12 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/storage/page/bufpage.c,v 1.51 2003/01/11 05:01:03 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/storage/page/bufpage.c,v 1.52 2003/03/28 20:17:13 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
 
-#include <sys/file.h>
-
 #include "storage/bufpage.h"
 
 
@@ -48,6 +46,51 @@ PageInit(Page page, Size pageSize, Size specialSize)
 }
 
 
+/*
+ * PageHeaderIsValid
+ *		Check that the header fields of a page appear valid.
+ *
+ * This is called when a page has just been read in from disk.  The idea is
+ * to cheaply detect trashed pages before we go nuts following bogus item
+ * pointers, testing invalid transaction identifiers, etc.
+ *
+ * It turns out to be necessary to allow zeroed pages here too.  Even though
+ * this routine is *not* called when deliberately adding a page to a relation,
+ * there are scenarios in which a zeroed page might be found in a table.
+ * (Example: a backend extends a relation, then crashes before it can write
+ * any WAL entry about the new page.  The kernel will already have the
+ * zeroed page in the file, and it will stay that way after restart.)  So we
+ * allow zeroed pages here, and are careful that the page access macros
+ * treat such a page as empty and without free space.  Eventually, VACUUM
+ * will clean up such a page and make it usable.
+ */
+bool
+PageHeaderIsValid(PageHeader page)
+{
+	char	   *pagebytes;
+	int			i;
+
+	/* Check normal case */
+	if (PageGetPageSize(page) == BLCKSZ &&
+		PageGetPageLayoutVersion(page) == PG_PAGE_LAYOUT_VERSION &&
+		page->pd_lower >= SizeOfPageHeaderData &&
+		page->pd_lower <= page->pd_upper &&
+		page->pd_upper <= page->pd_special &&
+		page->pd_special <= BLCKSZ &&
+		page->pd_special == MAXALIGN(page->pd_special))
+		return true;
+
+	/* Check all-zeroes case */
+	pagebytes = (char *) page;
+	for (i = 0; i < BLCKSZ; i++)
+	{
+		if (pagebytes[i] != 0)
+			return false;
+	}
+	return true;
+}
+
+
 /* ----------------
  *		PageAddItem
  *

src/backend/utils/misc/guc.c

@@ -5,7 +5,7 @@
  * command, configuration file, and command line options.
  * See src/backend/utils/misc/README for more information.
  *
- * $Header: /cvsroot/pgsql/src/backend/utils/misc/guc.c,v 1.117 2003/03/20 04:51:44 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/utils/misc/guc.c,v 1.118 2003/03/28 20:17:13 tgl Exp $
  *
  * Copyright 2000 by PostgreSQL Global Development Group
  * Written by Peter Eisentraut <peter_e@gmx.net>.
@@ -357,6 +357,10 @@ static struct config_bool
 		{"fsync", PGC_SIGHUP}, &enableFsync,
 		true, NULL, NULL
 	},
+	{
+		{"zero_damaged_pages", PGC_SUSET}, &zero_damaged_pages,
+		false, NULL, NULL
+	},
 	{
 		{"silent_mode", PGC_POSTMASTER}, &SilentMode,
 		false, NULL, NULL

src/backend/utils/misc/postgresql.conf.sample

@@ -213,6 +213,6 @@
 #sql_inheritance = true
 #transform_null_equals = false
 #statement_timeout = 0		# 0 is disabled, in milliseconds
+#zero_damaged_pages = false     # set this true only for disaster recovery
 #db_user_namespace = false
 #preload_libraries = ''
-