pg_computemaxlsn.patch

*** a/contrib/Makefile
--- b/contrib/Makefile
***************
*** 31,36 **** SUBDIRS = \
--- 31,37 ----
  		passwordcheck	\
  		pg_archivecleanup \
  		pg_buffercache	\
+ 		pg_computemaxlsn \
  		pg_freespacemap \
  		pg_standby	\
  		pg_stat_statements \
*** /dev/null
--- b/contrib/pg_computemaxlsn/Makefile
***************
*** 0 ****
--- 1,22 ----
+ # contrib/pg_computemaxlsn/Makefile
+ 
+ PGFILEDESC = "pg_computemaxlsn - an utility to find max LSN from data pages"
+ PGAPPICON = win32
+ 
+ PROGRAM  = pg_computemaxlsn
+ OBJS = pg_computemaxlsn.o $(WIN32RES)
+ 
+ PG_CPPFLAGS  = -I$(srcdir)
+ PG_LIBS = $(libpq_pgport)
+ 
+ 
+ ifdef USE_PGXS
+ PG_CONFIG = pg_config
+ PGXS := $(shell $(PG_CONFIG) --pgxs)
+ include $(PGXS)
+ else
+ subdir = contrib/pg_computemaxlsn
+ top_builddir = ../..
+ include $(top_builddir)/src/Makefile.global
+ include $(top_srcdir)/contrib/contrib-global.mk
+ endif
*** /dev/null
--- b/contrib/pg_computemaxlsn/pg_computemaxlsn.c
***************
*** 0 ****
--- 1,502 ----
+ /*-------------------------------------------------------------------------
+  *
+  * pg_computemaxlsn.c
+  *	  A utility to compute the maximum LSN in data pages 
+  *
+  * Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group
+  * Portions Copyright (c) 1994, Regents of the University of California
+  *
+  * IDENTIFICATION
+  * contrib/pg_computemaxlsn/pg_computemaxlsn.c
+  *
+  *-------------------------------------------------------------------------
+  */
+ 
+ /*
+  * We have to use postgres.h not postgres_fe.h here, because there's so much
+  * backend-only stuff for reading data files we need.  But we need a
+  * frontend-ish environment otherwise.	Hence this ugly hack.
+  */
+ #define FRONTEND 1
+ 
+ #include "postgres.h"
+ 
+ #include <dirent.h>
+ #include <fcntl.h>
+ #include <locale.h>
+ #include <sys/stat.h>
+ #include <sys/time.h>
+ #include <time.h>
+ #include <unistd.h>
+ #ifdef HAVE_GETOPT_H
+ #include <getopt.h>
+ #endif
+ 
+ #include "access/xlog_internal.h"
+ #include "catalog/catalog.h"
+ #include "storage/bufpage.h"
+ #include "storage/fd.h"
+ 
+ /* Page header size */
+ #define PAGEHDRSZ (sizeof(PageHeaderData))
+ 
+ /*
+  * relfile nodename validation allow only file name start with digit
+  */
+ #define validateRelfilenodename(name) ((name[0] >= '0') && (name[0] <= '9'))
+ 
+ extern int	optind;
+ extern char *optarg;
+ static const char *progname;
+ 
+ static void FindMaxLSNinFile(char *filename, XLogRecPtr *maxlsn);
+ static void FindMaxLSNinDir(char *path, XLogRecPtr *maxlsn);
+ static void FindMaxLSNinPgData(XLogRecPtr *maxlsn);
+ static void usage(void);
+ 
+ int
+ main(int argc, char *argv[])
+ {
+ 	int			c;
+ 	char	   *DataDir;
+ 	int			fd;
+ 	char		path[MAXPGPATH];
+ 	bool		print_max_lsn = false;
+ 	bool		print_pgdata_max_lsn = false;
+ 	char	   *LsnSearchPath = NULL;
+ 	uint64		maxLSN = 0;
+ 	XLogSegNo	logSegNo = 0;
+ 
+ 	set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pg_computemaxlsn"));
+ 
+ 	progname = get_progname(argv[0]);
+ 
+ 	if (argc > 1)
+ 	{
+ 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
+ 		{
+ 			usage();
+ 			exit(0);
+ 		}
+ 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
+ 		{
+ 			puts("pg_computemaxlsn (PostgreSQL) " PG_VERSION);
+ 			exit(0);
+ 		}
+ 	}
+ 
+ 	while ((c = getopt(argc, argv, "p:P")) != -1)
+ 	{
+ 		switch (c)
+ 		{
+ 			case 'p':
+ 				print_max_lsn = true;
+ 				LsnSearchPath = optarg;
+ 				break;
+ 
+ 			case 'P':
+ 				print_pgdata_max_lsn = true;
+ 				break;
+ 
+ 			default:
+ 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
+ 				exit(1);
+ 		}
+ 	}
+ 
+ 	if (optind == argc)
+ 	{
+ 		fprintf(stderr, _("%s: no data directory specified\n"), progname);
+ 		fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
+ 		exit(1);
+ 	}
+ 
+ 	/*
+ 	 * Don't allow pg_computemaxlsn to be run as root, to avoid overwriting the
+ 	 * ownership of files in the data directory. We need only check for root
+ 	 * -- any other user won't have sufficient permissions to modify files in
+ 	 * the data directory.
+ 	 */
+ #ifndef WIN32
+ 	if (geteuid() == 0)
+ 	{
+ 		fprintf(stderr, _("%s: cannot be executed by \"root\"\n"),
+ 				progname);
+ 		fprintf(stderr, _("You must run %s as the PostgreSQL superuser.\n"),
+ 				progname);
+ 		exit(1);
+ 	}
+ #endif
+ 
+ 	DataDir = argv[optind];
+ 
+ 	if (chdir(DataDir) < 0)
+ 	{
+ 		fprintf(stderr, _("%s: could not change directory to \"%s\": %s\n"),
+ 				progname, DataDir, strerror(errno));
+ 		exit(1);
+ 	}
+ 
+ 	/*
+ 	 * Check for a postmaster lock file --- if there is one, refuse to
+ 	 * proceed, on grounds we might be interfering with a live installation.
+ 	 */
+ 	snprintf(path, MAXPGPATH, "postmaster.pid");
+ 
+ 	if ((fd = open(path, O_RDONLY, 0)) < 0)
+ 	{
+ 		if (errno != ENOENT)
+ 		{
+ 			fprintf(stderr, _("%s: could not open file \"%s\" for reading: %s\n"), progname, path, strerror(errno));
+ 			exit(1);
+ 		}
+ 	}
+ 	else
+ 	{
+ 		fprintf(stderr, _("%s: lock file \"%s\" exists\n"
+ 						  "Is a server running?  If not, delete the lock file and try again.\n"),
+ 				progname, path);
+ 		exit(1);
+ 	}
+ 	
+ 	if (print_pgdata_max_lsn)
+ 	{
+ 		FindMaxLSNinPgData(&maxLSN);
+ 	}
+ 	else
+ 	{
+ 		struct stat fst;
+ 
+ 		if (stat(LsnSearchPath, &fst) < 0)
+ 		{
+ 			if (errno == ENOENT)
+ 			{
+ 				fprintf(stderr, _("%s: file or directory \"%s\" does not exists"),
+ 						progname, LsnSearchPath);
+ 			}
+ 			else
+ 			{
+ 				fprintf(stderr, _("%s: file or directory \"%s\" exists\n"
+ 								  "\n"),
+ 						progname, LsnSearchPath);
+ 			}
+ 			exit(1);
+ 		}
+ 
+ 		if (S_ISDIR(fst.st_mode))
+ 		{
+ 			FindMaxLSNinDir(LsnSearchPath, &maxLSN);
+ 		}
+ 		else
+ 		{
+ 			FindMaxLSNinFile(LsnSearchPath, &maxLSN);
+ 		}
+ 	}
+ 
+ 	XLByteToSeg(maxLSN, logSegNo);
+ 
+ 	printf ("Maximum LSN found is: " UINT64_FORMAT ", "
+ 			"WAL segment file name (fileid,seg): %08X%08X\n",
+ 			maxLSN,
+ 			(uint32) ((logSegNo) / XLogSegmentsPerXLogId),
+ 			(uint32) ((logSegNo) % XLogSegmentsPerXLogId));
+ 
+ 	return 0;
+ }
+ 
+ 
+ /*
+  * PageHeaderIsValid: Check page is valid or not
+  */
+ bool
+ PageHeaderIsValid(PageHeader page)
+ {
+ 	char	   *pagebytes;
+ 	int			i;
+ 
+ 	/* Check normal case */
+ 	if (PageGetPageSize(page) == BLCKSZ &&
+ 		PageGetPageLayoutVersion(page) == PG_PAGE_LAYOUT_VERSION &&
+ 		(page->pd_flags & ~PD_VALID_FLAG_BITS) == 0 &&
+ 		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 till page header; this is used only to log the page
+ 	 * details even we detect invalid page we will continue to nex pages
+ 	 */
+ 	pagebytes = (char *) page;
+ 	for (i = 0; i < PAGEHDRSZ; i++)
+ 	{
+ 		if (pagebytes[i] != 0)
+ 			return false;
+ 	}
+ 	return true;
+ }
+ 
+ 
+ /*
+  * Read the maximum LSN number in the one of data file (relnode file).
+  *
+  */
+ static void
+ FindMaxLSNinFile(char *filename, XLogRecPtr *maxlsn)
+ {
+ 	XLogRecPtr	pagelsn;
+ 	off_t		len,
+ 				seekpos;
+ 	uint32		nblocks,
+ 				blocknum;
+ 	char		buffer[PAGEHDRSZ];
+ 	int			nbytes;
+ 	int			fd;
+ 
+ 	if ((fd = open(filename, O_RDONLY | PG_BINARY, 0)) < 0)
+ 	{
+ 		/*
+ 		 * If file does not exist or or we can't read it. give error
+ 		 */
+ 		fprintf(stderr, _("%s: could not open file \"%s\" for reading: %s\n"),
+ 				progname, filename, strerror(errno));
+ 		return;
+ 	}
+ 
+ 	/* Calculate the number of pages in file */
+ 	len = lseek(fd, 0L, SEEK_END);
+ 	if (len < 0)
+ 	{
+ 		close(fd);
+ 		fprintf(stderr, _("%s: .. file \"%s\" for seeking: %s\n"),
+ 				progname, filename, strerror(errno));
+ 		return;
+ 	}
+ 
+ 	nblocks = (len / BLCKSZ);
+ 	if (nblocks > RELSEG_SIZE)
+ 	{
+ 		/*
+ 		 * In one relfilenode file length can't be more that RELSEG_SIZE
+ 		 */
+ 		close(fd);
+ 		fprintf(stderr, _("%s: .. file \"%s\" legth is more than RELSEG_SIZE.\n"),
+ 				progname, filename);
+ 		return;
+ 	}
+ 
+ 	/*
+ 	 * Read the only page header and validate; if we find invalid page log the
+ 	 * details of page and continue to next page.
+ 	 */
+ 	seekpos = 0;
+ 	for (blocknum = 0; blocknum < nblocks; blocknum++)
+ 	{
+ 		len = lseek(fd, seekpos, SEEK_SET);
+ 		if (len != seekpos)
+ 		{
+ 			close(fd);
+ 			fprintf(stderr, _("%s: could not seek to next page  \"%s\": %s\n"),
+ 					progname, filename, strerror(errno));
+ 			return;
+ 		}
+ 
+ 		nbytes = read(fd, buffer, PAGEHDRSZ);
+ 		if (nbytes < 0)
+ 		{
+ 			close(fd);
+ 			fprintf(stderr, _("%s: could not read file \"%s\": %s\n"),
+ 					progname, filename, strerror(errno));
+ 			return;
+ 		}
+ 
+ 		if (PageHeaderIsValid((PageHeader) buffer))
+ 		{
+ 			pagelsn = PageGetLSN(buffer);
+ 			if (XLByteLE(*maxlsn, pagelsn))
+ 			{
+ 				*maxlsn = pagelsn;
+ 			}
+ 		}
+ 		else
+ 		{
+ 			/*
+ 			 * If page is invalid log the error and continue
+ 			 */
+ 			fprintf(stderr, _("%s: Invalid page found in file \"%s\" pagid:%d\n"),
+ 					progname, filename, blocknum);
+ 		}
+ 		seekpos += (off_t) BLCKSZ;
+ 	}
+ 
+ 	close(fd);
+ 	return;
+ }
+ 
+ /*
+  * Read the maximum LSN number in current directory; ignore sub directories.
+  */
+ static void
+ FindMaxLSNinDir(char *path, XLogRecPtr *maxlsn)
+ {
+ 	DIR		   *dir;
+ 	struct dirent *de;
+ 	char		pathbuf[MAXPGPATH];
+ 	struct stat statbuf;
+ 
+ 	dir = opendir(path);
+ 	if (NULL == dir)
+ 	{
+ 		fprintf(stderr, _("%s: could not open directory \"%s\": %s\n"),
+ 				progname, path, strerror(errno));
+ 		return;
+ 	}
+ 
+ 	while ((de = readdir(dir)) != NULL)
+ 	{
+ 		/* Skip special stuff */
+ 		if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0)
+ 			continue;
+ 
+ 		/* Skip temporary files */
+ 		if (strncmp(de->d_name,
+ 					PG_TEMP_FILE_PREFIX,
+ 					strlen(PG_TEMP_FILE_PREFIX)) == 0)
+ 			continue;
+ 
+ 		/*
+ 		 * Skip all the local/global temporary files, and read and read all
+ 		 * reamining relfinenode files
+ 		 */
+ 		if (!validateRelfilenodename(de->d_name))
+ 			continue;
+ 
+ 		snprintf(pathbuf, MAXPGPATH, "%s/%s", path, de->d_name);
+ 
+ 		if (stat(pathbuf, &statbuf) != 0)
+ 		{
+ 			if (errno != ENOENT)
+ 			{
+ 				fprintf(stderr, "could not stat file or directory \"%s\"",
+ 						pathbuf);
+ 			}
+ 			/* If the file went away while scanning, it's no error. */
+ 			continue;
+ 		}
+ 
+ 		/*
+ 		 * Skip all directories
+ 		 */
+ 		if (!S_ISDIR(statbuf.st_mode))
+ 		{
+ 			FindMaxLSNinFile(pathbuf, maxlsn);
+ 		}
+ 	}
+ 
+ 	closedir(dir);
+ 	return;
+ }
+ 
+ /*
+  * Read the maximum LSN number in the DATA directory.
+  */
+ static void
+ FindMaxLSNinPgData(XLogRecPtr *maxlsn)
+ {
+ 	DIR		   *dir,
+ 			   *dir2;
+ 	struct dirent *de,
+ 			   *de2;
+ 	char		pathbuf[MAXPGPATH],
+ 				pathbuf2[MAXPGPATH];
+ 
+ 	/*
+ 	 * scan all the relfilenodes in global directory
+ 	 */
+ 	FindMaxLSNinDir("global", maxlsn);
+ 
+ 	/*
+ 	 * scan all the relfilenodes in base directory like base/<database-id>
+ 	 */
+ 	dir = opendir("base");
+ 	if (NULL == dir)
+ 	{
+ 		fprintf(stderr, _("%s: could not open directory \"%s\": %s\n"),
+ 				progname, "base", strerror(errno));
+ 		return;
+ 	}
+ 
+ 	while ((de = readdir(dir)) != NULL)
+ 	{
+ 		/* Skip special stuff */
+ 		if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0)
+ 			continue;
+ 
+ 		/* Skip template database */
+ 		if (strcmp(de->d_name, "0") == 0 || strcmp(de->d_name, "1") == 0)
+ 			continue;
+ 
+ 		snprintf(pathbuf, MAXPGPATH, "%s/%s", "base", de->d_name);
+ 
+ 		FindMaxLSNinDir(pathbuf, maxlsn);
+ 	}
+ 	closedir(dir);
+ 
+ 	/* Scan all tablespaces */
+ 	dir = opendir("pg_tblspc");
+ 	if (NULL == dir)
+ 	{
+ 		fprintf(stderr, _("%s: could not open directory \"%s\": %s\n"),
+ 				progname, "pg_tblspc", strerror(errno));
+ 		return;
+ 	}
+ 
+ 	while ((de = readdir(dir)) != NULL)
+ 	{
+ 		/* Skip special stuff */
+ 		if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0)
+ 			continue;
+ 
+ 		/*
+ 		 * Scan all directories in tablespace
+ 		 * ./pg_tblspc/tablespaceid/TABLESPACE_VERSION_DIRECTORY/ *
+ 		 */
+ 		snprintf(pathbuf, MAXPGPATH, "%s/%s/%s", "pg_tblspc", de->d_name, TABLESPACE_VERSION_DIRECTORY);
+ 		dir2 = opendir(pathbuf);
+ 		if (NULL == dir2)
+ 		{
+ 			fprintf(stderr, _("%s: could not open directory \"%s\": %s\n"),
+ 					progname, pathbuf, strerror(errno));
+ 			return;
+ 		}
+ 
+ 		while ((de2 = readdir(dir2)) != NULL)
+ 		{
+ 			/* Skip special stuff */
+ 			if (strcmp(de2->d_name, ".") == 0 || strcmp(de2->d_name, "..") == 0)
+ 				continue;
+ 
+ 			snprintf(pathbuf2, MAXPGPATH, "%s/%s", pathbuf, de2->d_name);
+ 
+ 			FindMaxLSNinDir(pathbuf2, maxlsn);
+ 		}
+ 		closedir(dir2);
+ 	}
+ 	closedir(dir);
+ 
+ 	return;
+ }
+ 
+ static void
+ usage(void)
+ {
+ 	printf(_("%s compute the maximum LSN in PostgreSQL data pages.\n\n"), progname);
+ 	printf(_("Usage:\n  %s [OPTION]... DATADIR\n\n"), progname);
+ 	printf(_("Options:\n"));
+ 	printf(_("  -p {file | dir}  print max LSN from specified file or directory path\n"));
+ 	printf(_("  -P               print max LSN from whole database\n"));
+ 	printf(_("  -?, --help       show this help, then exit\n"));
+ 	printf(_("\nReport bugs to <pgsql-bugs@postgresql.org>.\n"));
+ }
*** a/doc/src/sgml/ref/allfiles.sgml
--- b/doc/src/sgml/ref/allfiles.sgml
***************
*** 177,182 **** Complete list of usable sgml source files in this directory.
--- 177,183 ----
  <!ENTITY pgDumpall          SYSTEM "pg_dumpall.sgml">
  <!ENTITY pgReceivexlog      SYSTEM "pg_receivexlog.sgml">
  <!ENTITY pgResetxlog        SYSTEM "pg_resetxlog.sgml">
+ <!ENTITY pgCompuremaxlsn    SYSTEM "pg_computemaxlsn.sgml">
  <!ENTITY pgRestore          SYSTEM "pg_restore.sgml">
  <!ENTITY postgres           SYSTEM "postgres-ref.sgml">
  <!ENTITY postmaster         SYSTEM "postmaster.sgml">
*** /dev/null
--- b/doc/src/sgml/ref/pg_computemaxlsn.sgml
***************
*** 0 ****
--- 1,74 ----
+ <!--
+ doc/src/sgml/ref/pg_computemaxlsn.sgml
+ PostgreSQL documentation
+ -->
+ 
+ <refentry id="APP-PGCOMPUTEMAXLSN">
+  <refmeta>
+   <refentrytitle><application>pg_computemaxlsn</application></refentrytitle>
+   <manvolnum>1</manvolnum>
+   <refmiscinfo>Application</refmiscinfo>
+  </refmeta>
+ 
+  <refnamediv>
+   <refname>pg_computemaxlsn</refname>
+   <refpurpose>computes the maximum LSN in database of a <productname>PostgreSQL</productname> database cluster</refpurpose>
+  </refnamediv>
+ 
+  <indexterm zone="app-pgcomputemaxlsn">
+   <primary>pg_computemaxlsn</primary>
+  </indexterm>
+ 
+  <refsynopsisdiv>
+   <cmdsynopsis>
+    <command>pg_computemaxlsn</command>
+    <arg choice="opt"><option>-P</option></arg>
+    <arg choice="opt"><option>-p</option> <replaceable class="parameter">file-name</replaceable> | <replaceable class="parameter">folder-name</replaceable></arg>
+    <arg choice="plain"><replaceable>datadir</replaceable></arg>
+   </cmdsynopsis>
+  </refsynopsisdiv>
+ 
+  <refsect1 id="R1-APP-PGCOMPUTEMAXLSN-1">
+   <title>Description</title>
+   <para>
+    <command>pg_computemaxlsn</command> computes maximun LSN from database pages.
+   </para>
+ 
+   <para>
+    This utility can only be run by the user who installed the server, because
+    it requires read/write access to the data directory.
+    For safety reasons, you must specify the data directory on the command line.
+    <command>pg_computemaxlsn</command> does not use the environment variable
+    <envar>PGDATA</>.
+   </para>
+ 
+   <para>
+    The <option>-P</> for computing maximum LSN from all the pages in data directory, and  or for from
+    <option>-p <filename>file-name | folder-name</></> for computing maximun LSN from specific 
+    file or folder (excluding sub-directories).   
+   </para>
+ 
+   <para>
+    The <option>-V</> and <option>--version</> options print
+    the <application>pg_computemaxlsn</application> version and exit.  The
+    options <option>-?</> and <option>--help</> show supported arguments,
+    and exit.
+   </para>
+ 
+  </refsect1>
+ 
+  <refsect1>
+   <title>Notes</title>
+ 
+   <para>
+    This command must not be used when the server is
+    running.  <command>pg_computemaxlsn</command> will refuse to start up if
+    it finds a server lock file in the data directory.  If the
+    server crashed then a lock file might have been left
+    behind; in that case you can remove the lock file to allow
+    <command>pg_computemaxlsn</command> to run.  But before you do
+    so, make doubly certain that there is no server process still alive.
+   </para>
+  </refsect1>
+ 
+ </refentry>
*** a/doc/src/sgml/ref/pg_resetxlog.sgml
--- b/doc/src/sgml/ref/pg_resetxlog.sgml
***************
*** 135,140 **** PostgreSQL documentation
--- 135,150 ----
        largest entry in <filename>pg_xlog</>, use <literal>-l 00000001000000320000004B</> or higher.
       </para>
  
+      <para>
+       If <command>pg_resetxlog</command> complains that it cannot determine
+       valid data for <filename>pg_control</>, and if you do not have or corrupted
+       WAL segment files in the directory <filename>pg_xlog</> under the data directory,
+       then to identify larger WAL segment file from data files we can use utility <command>pg_computemaxlsn</command>
+       with <option>-P</> option for finding maximum LSN from the data directory or 
+       for from specific file or folder <option>-p <filename>file-name | folder-name</></>.
+       Once larger WAL segment file is found use <option>-l</> option for setting the value.
+      </para>
+ 
       <note>
        <para>
         <command>pg_resetxlog</command> itself looks at the files in
*** a/doc/src/sgml/reference.sgml
--- b/doc/src/sgml/reference.sgml
***************
*** 248,253 ****
--- 248,254 ----
     &pgControldata;
     &pgCtl;
     &pgResetxlog;
+    &pgCompuremaxlsn;
     &postgres;
     &postmaster;