~drizzle-trunk/drizzle/development

/*****************************************************************************

Copyright (C) 1996, 2010, Innobase Oy. All Rights Reserved.

This program is free software; you can redistribute it and/or modify it under

the terms of the GNU General Public License as published by the Free Software

Foundation; version 2 of the License.

This program is distributed in the hope that it will be useful, but WITHOUT

ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS

FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with

this program; if not, write to the Free Software Foundation, Inc., 51 Franklin

St, Fifth Floor, Boston, MA 02110-1301 USA

*****************************************************************************/

/**************************************************//**

@file trx/trx0sys.c

Transaction system

Created 3/26/1996 Heikki Tuuri

*******************************************************/

#include "trx0sys.h"

#ifdef UNIV_NONINL

#include "trx0sys.ic"

#endif

#ifndef UNIV_HOTBACKUP

#include "fsp0fsp.h"

#include "mtr0log.h"

#include "mtr0log.h"

#include "trx0trx.h"

#include "trx0rseg.h"

#include "trx0undo.h"

#include "srv0srv.h"

#include "trx0purge.h"

#include "log0log.h"

#include "log0recv.h"

#include "os0file.h"

#include "read0read.h"

/** The file format tag structure with id and name. */

struct file_format_struct {

	ulint		id;		/*!< id of the file format */

	const char*	name;		/*!< text representation of the

					file format */

	mutex_t		mutex;		/*!< covers changes to the above

					fields */

};

/** The file format tag */

typedef struct file_format_struct	file_format_t;

/** The transaction system */

UNIV_INTERN trx_sys_t*		trx_sys		= NULL;

/** The doublewrite buffer */

UNIV_INTERN trx_doublewrite_t*	trx_doublewrite = NULL;

/** The following is set to TRUE when we are upgrading from pre-4.1

format data files to the multiple tablespaces format data files */

UNIV_INTERN ibool	trx_doublewrite_must_reset_space_ids	= FALSE;

/** Set to TRUE when the doublewrite buffer is being created */

UNIV_INTERN ibool	trx_doublewrite_buf_is_being_created = FALSE;

/** The following is TRUE when we are using the database in the

post-4.1 format, i.e., we have successfully upgraded, or have created

a new database installation */

UNIV_INTERN ibool	trx_sys_multiple_tablespace_format	= FALSE;

/** In a MySQL replication slave, in crash recovery we store the master log

file name and position here. */

/* @{ */

/** Master binlog file name */

UNIV_INTERN char	trx_sys_mysql_master_log_name[TRX_SYS_MYSQL_LOG_NAME_LEN];

/** Master binlog file position.  We have successfully got the updates

up to this position.  -1 means that no crash recovery was needed, or

there was no master log position info inside InnoDB.*/

UNIV_INTERN ib_int64_t	trx_sys_mysql_master_log_pos	= -1;

/* @} */

/** If this MySQL server uses binary logging, after InnoDB has been inited

and if it has done a crash recovery, we store the binlog file name and position

here. */

/* @{ */

/** Binlog file name */

UNIV_INTERN char	trx_sys_mysql_bin_log_name[TRX_SYS_MYSQL_LOG_NAME_LEN];

/** Binlog file position, or -1 if unknown */

UNIV_INTERN ib_int64_t	trx_sys_mysql_bin_log_pos	= -1;

/* @} */

#endif /* !UNIV_HOTBACKUP */

/** List of animal names representing file format. */

static const char*	file_format_name_map[] = {

	"Antelope",

	"Barracuda",

	"Cheetah",

	"Dragon",

	"Elk",

	"Fox",

	"Gazelle",

	"Hornet",

	"Impala",

	"Jaguar",

	"Kangaroo",

	"Leopard",

	"Moose",

	"Nautilus",

	"Ocelot",

	"Porpoise",

	"Quail",

	"Rabbit",

	"Shark",

	"Tiger",

	"Urchin",

	"Viper",

	"Whale",

	"Xenops",

	"Yak",

	"Zebra"

};

/** The number of elements in the file format name array. */

static const ulint	FILE_FORMAT_NAME_N

	= sizeof(file_format_name_map) / sizeof(file_format_name_map[0]);

#ifdef UNIV_PFS_MUTEX

/* Key to register the mutex with performance schema */

UNIV_INTERN mysql_pfs_key_t	trx_doublewrite_mutex_key;

UNIV_INTERN mysql_pfs_key_t	file_format_max_mutex_key;

#endif /* UNIV_PFS_MUTEX */

#ifndef UNIV_HOTBACKUP

/** This is used to track the maximum file format id known to InnoDB. It's

updated via SET GLOBAL innodb_file_format_max = 'x' or when we open

or create a table. */

static	file_format_t	file_format_max;

/****************************************************************//**

Determines if a page number is located inside the doublewrite buffer.

@return TRUE if the location is inside the two blocks of the

doublewrite buffer */

UNIV_INTERN

ibool

trx_doublewrite_page_inside(

/*========================*/

	ulint	page_no)	/*!< in: page number */

{

	if (trx_doublewrite == NULL) {

		return(FALSE);

	}

	if (page_no >= trx_doublewrite->block1

	    && page_no < trx_doublewrite->block1

	    + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {

		return(TRUE);

	}

	if (page_no >= trx_doublewrite->block2

	    && page_no < trx_doublewrite->block2

	    + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {

		return(TRUE);

	}

	return(FALSE);

}

/****************************************************************//**

Creates or initialializes the doublewrite buffer at a database start. */

static

void

trx_doublewrite_init(

/*=================*/

	byte*	doublewrite)	/*!< in: pointer to the doublewrite buf

				header on trx sys page */

{

  trx_doublewrite = static_cast<trx_doublewrite_t *>(mem_alloc(sizeof(trx_doublewrite_t)));

	/* Since we now start to use the doublewrite buffer, no need to call

	fsync() after every write to a data file */

#ifdef UNIV_DO_FLUSH

	os_do_not_call_flush_at_each_write = TRUE;

#endif /* UNIV_DO_FLUSH */

	mutex_create(trx_doublewrite_mutex_key,

		     &trx_doublewrite->mutex, SYNC_DOUBLEWRITE);

	trx_doublewrite->first_free = 0;

	trx_doublewrite->block1 = mach_read_from_4(

		doublewrite + TRX_SYS_DOUBLEWRITE_BLOCK1);

	trx_doublewrite->block2 = mach_read_from_4(

		doublewrite + TRX_SYS_DOUBLEWRITE_BLOCK2);

        trx_doublewrite->write_buf_unaligned = static_cast<byte *>(ut_malloc(

                                                                             (1 + 2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) * UNIV_PAGE_SIZE));

        trx_doublewrite->write_buf = static_cast<byte *>(ut_align(

                                                                  trx_doublewrite->write_buf_unaligned, UNIV_PAGE_SIZE));

        trx_doublewrite->buf_block_arr = static_cast<buf_page_t **>(mem_alloc(

                                                                             2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * sizeof(void*)));

}

/****************************************************************//**

Marks the trx sys header when we have successfully upgraded to the >= 4.1.x

multiple tablespace format. */

UNIV_INTERN

void

trx_sys_mark_upgraded_to_multiple_tablespaces(void)

/*===============================================*/

{

	buf_block_t*	block;

	byte*		doublewrite;

	mtr_t		mtr;

	/* We upgraded to 4.1.x and reset the space id fields in the

	doublewrite buffer. Let us mark to the trx_sys header that the upgrade

	has been done. */

	mtr_start(&mtr);

	block = buf_page_get(TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO,

			     RW_X_LATCH, &mtr);

	buf_block_dbg_add_level(block, SYNC_NO_ORDER_CHECK);

	doublewrite = buf_block_get_frame(block) + TRX_SYS_DOUBLEWRITE;

	mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED,

			 TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N,

			 MLOG_4BYTES, &mtr);

	mtr_commit(&mtr);

	/* Flush the modified pages to disk and make a checkpoint */

	log_make_checkpoint_at(IB_ULONGLONG_MAX, TRUE);

	trx_sys_multiple_tablespace_format = TRUE;

}

/****************************************************************//**

Creates the doublewrite buffer to a new InnoDB installation. The header of the

doublewrite buffer is placed on the trx system header page. */

UNIV_INTERN

void

trx_sys_create_doublewrite_buf(void)

/*================================*/

{

	buf_block_t*	block;

	buf_block_t*	block2;

#ifdef UNIV_SYNC_DEBUG

	buf_block_t*	new_block;

#endif /* UNIV_SYNC_DEBUG */

	byte*	doublewrite;

	byte*	fseg_header;

	ulint	page_no;

	ulint	prev_page_no;

	ulint	i;

	mtr_t	mtr;

	if (trx_doublewrite) {

		/* Already inited */

		return;

	}

start_again:

	mtr_start(&mtr);

	trx_doublewrite_buf_is_being_created = TRUE;

	block = buf_page_get(TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO,

			     RW_X_LATCH, &mtr);

	buf_block_dbg_add_level(block, SYNC_NO_ORDER_CHECK);

	doublewrite = buf_block_get_frame(block) + TRX_SYS_DOUBLEWRITE;

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC)

	    == TRX_SYS_DOUBLEWRITE_MAGIC_N) {

		/* The doublewrite buffer has already been created:

		just read in some numbers */

		trx_doublewrite_init(doublewrite);

		mtr_commit(&mtr);

		trx_doublewrite_buf_is_being_created = FALSE;

	} else {

		fprintf(stderr,

			"InnoDB: Doublewrite buffer not found:"

			" creating new\n");

		if (buf_pool_get_curr_size()

		    < ((2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE

			+ FSP_EXTENT_SIZE / 2 + 100)

		       * UNIV_PAGE_SIZE)) {

			fprintf(stderr,

				"InnoDB: Cannot create doublewrite buffer:"

				" you must\n"

				"InnoDB: increase your buffer pool size.\n"

				"InnoDB: Cannot continue operation.\n");

			exit(1);

		}

		block2 = fseg_create(TRX_SYS_SPACE, TRX_SYS_PAGE_NO,

				     TRX_SYS_DOUBLEWRITE

				     + TRX_SYS_DOUBLEWRITE_FSEG, &mtr);

		/* fseg_create acquires a second latch on the page,

		therefore we must declare it: */

		buf_block_dbg_add_level(block2, SYNC_NO_ORDER_CHECK);

		if (block2 == NULL) {

			fprintf(stderr,

				"InnoDB: Cannot create doublewrite buffer:"

				" you must\n"

				"InnoDB: increase your tablespace size.\n"

				"InnoDB: Cannot continue operation.\n");

			/* We exit without committing the mtr to prevent

			its modifications to the database getting to disk */

			exit(1);

		}

		fseg_header = buf_block_get_frame(block)

			+ TRX_SYS_DOUBLEWRITE + TRX_SYS_DOUBLEWRITE_FSEG;

		prev_page_no = 0;

		for (i = 0; i < 2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE

			     + FSP_EXTENT_SIZE / 2; i++) {

			page_no = fseg_alloc_free_page(fseg_header,

						       prev_page_no + 1,

						       FSP_UP, &mtr);

			if (page_no == FIL_NULL) {

				fprintf(stderr,

					"InnoDB: Cannot create doublewrite"

					" buffer: you must\n"

					"InnoDB: increase your"

					" tablespace size.\n"

					"InnoDB: Cannot continue operation.\n"

					);

				exit(1);

			}

			/* We read the allocated pages to the buffer pool;

			when they are written to disk in a flush, the space

			id and page number fields are also written to the

			pages. When we at database startup read pages

			from the doublewrite buffer, we know that if the

			space id and page number in them are the same as

			the page position in the tablespace, then the page

			has not been written to in doublewrite. */

#ifdef UNIV_SYNC_DEBUG

			new_block =

#endif /* UNIV_SYNC_DEBUG */

			buf_page_get(TRX_SYS_SPACE, 0, page_no,

				     RW_X_LATCH, &mtr);

			buf_block_dbg_add_level(new_block,

						SYNC_NO_ORDER_CHECK);

			if (i == FSP_EXTENT_SIZE / 2) {

				ut_a(page_no == FSP_EXTENT_SIZE);

				mlog_write_ulint(doublewrite

						 + TRX_SYS_DOUBLEWRITE_BLOCK1,

						 page_no, MLOG_4BYTES, &mtr);

				mlog_write_ulint(doublewrite

						 + TRX_SYS_DOUBLEWRITE_REPEAT

						 + TRX_SYS_DOUBLEWRITE_BLOCK1,

						 page_no, MLOG_4BYTES, &mtr);

			} else if (i == FSP_EXTENT_SIZE / 2

				   + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {

				ut_a(page_no == 2 * FSP_EXTENT_SIZE);

				mlog_write_ulint(doublewrite

						 + TRX_SYS_DOUBLEWRITE_BLOCK2,

						 page_no, MLOG_4BYTES, &mtr);

				mlog_write_ulint(doublewrite

						 + TRX_SYS_DOUBLEWRITE_REPEAT

						 + TRX_SYS_DOUBLEWRITE_BLOCK2,

						 page_no, MLOG_4BYTES, &mtr);

			} else if (i > FSP_EXTENT_SIZE / 2) {

				ut_a(page_no == prev_page_no + 1);

			}

			prev_page_no = page_no;

		}

		mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC,

				 TRX_SYS_DOUBLEWRITE_MAGIC_N,

				 MLOG_4BYTES, &mtr);

		mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC

				 + TRX_SYS_DOUBLEWRITE_REPEAT,

				 TRX_SYS_DOUBLEWRITE_MAGIC_N,

				 MLOG_4BYTES, &mtr);

		mlog_write_ulint(doublewrite

				 + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED,

				 TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N,

				 MLOG_4BYTES, &mtr);

		mtr_commit(&mtr);

		/* Flush the modified pages to disk and make a checkpoint */

		log_make_checkpoint_at(IB_ULONGLONG_MAX, TRUE);

		fprintf(stderr, "InnoDB: Doublewrite buffer created\n");

		trx_sys_multiple_tablespace_format = TRUE;

		goto start_again;

	}

}

/****************************************************************//**

At a database startup initializes the doublewrite buffer memory structure if

we already have a doublewrite buffer created in the data files. If we are

upgrading to an InnoDB version which supports multiple tablespaces, then this

function performs the necessary update operations. If we are in a crash

recovery, this function uses a possible doublewrite buffer to restore

half-written pages in the data files. */

UNIV_INTERN

void

trx_sys_doublewrite_init_or_restore_pages(

/*======================================*/

	ibool	restore_corrupt_pages)	/*!< in: TRUE=restore pages */

{

	byte*	buf;

	byte*	read_buf;

	byte*	unaligned_read_buf;

	ulint	block1;

	ulint	block2;

	ulint	source_page_no;

	byte*	page;

	byte*	doublewrite;

	ulint	space_id;

	ulint	page_no;

	ulint	i;

	/* We do the file i/o past the buffer pool */

        unaligned_read_buf = static_cast<byte *>(ut_malloc(2 * UNIV_PAGE_SIZE));

        read_buf = static_cast<byte *>(ut_align(unaligned_read_buf, UNIV_PAGE_SIZE));

	/* Read the trx sys header to check if we are using the doublewrite

	buffer */

	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO, 0,

	       UNIV_PAGE_SIZE, read_buf, NULL);

	doublewrite = read_buf + TRX_SYS_DOUBLEWRITE;

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC)

	    == TRX_SYS_DOUBLEWRITE_MAGIC_N) {

		/* The doublewrite buffer has been created */

		trx_doublewrite_init(doublewrite);

		block1 = trx_doublewrite->block1;

		block2 = trx_doublewrite->block2;

		buf = trx_doublewrite->write_buf;

	} else {

		goto leave_func;

	}

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED)

	    != TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N) {

		/* We are upgrading from a version < 4.1.x to a version where

		multiple tablespaces are supported. We must reset the space id

		field in the pages in the doublewrite buffer because starting

		from this version the space id is stored to

		FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID. */

		trx_doublewrite_must_reset_space_ids = TRUE;

		fprintf(stderr,

			"InnoDB: Resetting space id's in the"

			" doublewrite buffer\n");

	} else {

		trx_sys_multiple_tablespace_format = TRUE;

	}

	/* Read the pages from the doublewrite buffer to memory */

	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, block1, 0,

	       TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,

	       buf, NULL);

	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, block2, 0,

	       TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,

	       buf + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,

	       NULL);

	/* Check if any of these pages is half-written in data files, in the

	intended position */

	page = buf;

	for (i = 0; i < TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * 2; i++) {

		page_no = mach_read_from_4(page + FIL_PAGE_OFFSET);

		if (trx_doublewrite_must_reset_space_ids) {

			space_id = 0;

			mach_write_to_4(page

					+ FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID, 0);

			/* We do not need to calculate new checksums for the

			pages because the field .._SPACE_ID does not affect

			them. Write the page back to where we read it from. */

			if (i < TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {

				source_page_no = block1 + i;

			} else {

				source_page_no = block2

					+ i - TRX_SYS_DOUBLEWRITE_BLOCK_SIZE;

			}

			fil_io(OS_FILE_WRITE, TRUE, 0, 0, source_page_no, 0,

			       UNIV_PAGE_SIZE, page, NULL);

			/* printf("Resetting space id in page %lu\n",

			source_page_no); */

		} else {

			space_id = mach_read_from_4(

				page + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);

		}

		if (!restore_corrupt_pages) {

			/* The database was shut down gracefully: no need to

			restore pages */

		} else if (!fil_tablespace_exists_in_mem(space_id)) {

			/* Maybe we have dropped the single-table tablespace

			and this page once belonged to it: do nothing */

		} else if (!fil_check_adress_in_tablespace(space_id,

							   page_no)) {

			fprintf(stderr,

				"InnoDB: Warning: a page in the"

				" doublewrite buffer is not within space\n"

				"InnoDB: bounds; space id %lu"

				" page number %lu, page %lu in"

				" doublewrite buf.\n",

				(ulong) space_id, (ulong) page_no, (ulong) i);

		} else if (space_id == TRX_SYS_SPACE

			   && ((page_no >= block1

				&& page_no

				< block1 + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE)

			       || (page_no >= block2

				   && page_no

				   < (block2

				      + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE)))) {

			/* It is an unwritten doublewrite buffer page:

			do nothing */

		} else {

			ulint	zip_size = fil_space_get_zip_size(space_id);

			/* Read in the actual page from the file */

			fil_io(OS_FILE_READ, TRUE, space_id, zip_size,

			       page_no, 0,

			       zip_size ? zip_size : UNIV_PAGE_SIZE,

			       read_buf, NULL);

			/* Check if the page is corrupt */

			if (UNIV_UNLIKELY

			    (buf_page_is_corrupted(read_buf, zip_size))) {

				fprintf(stderr,

					"InnoDB: Warning: database page"

					" corruption or a failed\n"

					"InnoDB: file read of"

					" space %lu page %lu.\n"

					"InnoDB: Trying to recover it from"

					" the doublewrite buffer.\n",

					(ulong) space_id, (ulong) page_no);

				if (buf_page_is_corrupted(page, zip_size)) {

					fprintf(stderr,

						"InnoDB: Dump of the page:\n");

					buf_page_print(read_buf, zip_size);

					fprintf(stderr,

						"InnoDB: Dump of"

						" corresponding page"

						" in doublewrite buffer:\n");

					buf_page_print(page, zip_size);

					fprintf(stderr,

						"InnoDB: Also the page in the"

						" doublewrite buffer"

						" is corrupt.\n"

						"InnoDB: Cannot continue"

						" operation.\n"

						"InnoDB: You can try to"

						" recover the database"

						" with the my.cnf\n"

						"InnoDB: option:\n"

						"InnoDB:"

						" innodb_force_recovery=6\n");

					exit(1);

				}

				/* Write the good page from the

				doublewrite buffer to the intended

				position */

				fil_io(OS_FILE_WRITE, TRUE, space_id,

				       zip_size, page_no, 0,

				       zip_size ? zip_size : UNIV_PAGE_SIZE,

				       page, NULL);

				fprintf(stderr,

					"InnoDB: Recovered the page from"

					" the doublewrite buffer.\n");

			}

		}

		page += UNIV_PAGE_SIZE;

	}

	fil_flush_file_spaces(FIL_TABLESPACE);

leave_func:

	ut_free(unaligned_read_buf);

}

/****************************************************************//**

Checks that trx is in the trx list.

@return	TRUE if is in */

UNIV_INTERN

ibool

trx_in_trx_list(

/*============*/

	trx_t*	in_trx)	/*!< in: trx */

{

	trx_t*	trx;

	ut_ad(mutex_own(&(kernel_mutex)));

	trx = UT_LIST_GET_FIRST(trx_sys->trx_list);

	while (trx != NULL) {

		if (trx == in_trx) {

			return(TRUE);

		}

		trx = UT_LIST_GET_NEXT(trx_list, trx);

	}

	return(FALSE);

}

/*****************************************************************//**

Writes the value of max_trx_id to the file based trx system header. */

UNIV_INTERN

void

trx_sys_flush_max_trx_id(void)

/*==========================*/

{

	trx_sysf_t*	sys_header;

	mtr_t		mtr;

	ut_ad(mutex_own(&kernel_mutex));

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	mlog_write_ull(sys_header + TRX_SYS_TRX_ID_STORE,

		       trx_sys->max_trx_id, &mtr);

	mtr_commit(&mtr);

}

/*****************************************************************//**

Updates the offset information about the end of the MySQL binlog entry

which corresponds to the transaction just being committed. In a MySQL

replication slave updates the latest master binlog position up to which

replication has proceeded. */

UNIV_INTERN

void

trx_sys_update_mysql_binlog_offset(

/*===============================*/

	const char*	file_name,/*!< in: MySQL log file name */

	ib_int64_t	offset,	/*!< in: position in that log file */

	ulint		field,	/*!< in: offset of the MySQL log info field in

				the trx sys header */

	mtr_t*		mtr)	/*!< in: mtr */

{

	trx_sysf_t*	sys_header;

	if (ut_strlen(file_name) >= TRX_SYS_MYSQL_LOG_NAME_LEN) {

		/* We cannot fit the name to the 512 bytes we have reserved */

		return;

	}

	sys_header = trx_sysf_get(mtr);

	if (mach_read_from_4(sys_header + field

			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)

	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mlog_write_ulint(sys_header + field

				 + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD,

				 TRX_SYS_MYSQL_LOG_MAGIC_N,

				 MLOG_4BYTES, mtr);

	}

	if (0 != strcmp((char*) (sys_header + field + TRX_SYS_MYSQL_LOG_NAME),

			file_name)) {

		mlog_write_string(sys_header + field

				  + TRX_SYS_MYSQL_LOG_NAME,

				  (byte*) file_name, 1 + ut_strlen(file_name),

				  mtr);

	}

	if (mach_read_from_4(sys_header + field

			     + TRX_SYS_MYSQL_LOG_OFFSET_HIGH) > 0

	    || (offset >> 32) > 0) {

		mlog_write_ulint(sys_header + field

				 + TRX_SYS_MYSQL_LOG_OFFSET_HIGH,

				 (ulint)(offset >> 32),

				 MLOG_4BYTES, mtr);

	}

	mlog_write_ulint(sys_header + field

			 + TRX_SYS_MYSQL_LOG_OFFSET_LOW,

			 (ulint)(offset & 0xFFFFFFFFUL),

			 MLOG_4BYTES, mtr);

}

/*****************************************************************//**

Stores the MySQL binlog offset info in the trx system header if

the magic number shows it valid, and print the info to stderr */

UNIV_INTERN

void

trx_sys_print_mysql_binlog_offset(void)

/*===================================*/

{

	trx_sysf_t*	sys_header;

	mtr_t		mtr;

	ulint		trx_sys_mysql_bin_log_pos_high;

	ulint		trx_sys_mysql_bin_log_pos_low;

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	if (mach_read_from_4(sys_header + TRX_SYS_MYSQL_LOG_INFO

			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)

	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mtr_commit(&mtr);

		return;

	}

	trx_sys_mysql_bin_log_pos_high = mach_read_from_4(

		sys_header + TRX_SYS_MYSQL_LOG_INFO

		+ TRX_SYS_MYSQL_LOG_OFFSET_HIGH);

	trx_sys_mysql_bin_log_pos_low = mach_read_from_4(

		sys_header + TRX_SYS_MYSQL_LOG_INFO

		+ TRX_SYS_MYSQL_LOG_OFFSET_LOW);

	trx_sys_mysql_bin_log_pos

		= (((ib_int64_t)trx_sys_mysql_bin_log_pos_high) << 32)

		+ (ib_int64_t)trx_sys_mysql_bin_log_pos_low;

	ut_memcpy(trx_sys_mysql_bin_log_name,

		  sys_header + TRX_SYS_MYSQL_LOG_INFO

		  + TRX_SYS_MYSQL_LOG_NAME, TRX_SYS_MYSQL_LOG_NAME_LEN);

	fprintf(stderr,

		"InnoDB: Last MySQL binlog file position %lu %lu,"

		" file name %s\n",

		trx_sys_mysql_bin_log_pos_high, trx_sys_mysql_bin_log_pos_low,

		trx_sys_mysql_bin_log_name);

	mtr_commit(&mtr);

}

/*****************************************************************//**

Prints to stderr the MySQL master log offset info in the trx system header if

the magic number shows it valid. */

UNIV_INTERN

void

trx_sys_print_mysql_master_log_pos(void)

/*====================================*/

{

	trx_sysf_t*	sys_header;

	mtr_t		mtr;

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	if (mach_read_from_4(sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO

			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)

	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mtr_commit(&mtr);

		return;

	}

	fprintf(stderr,

		"InnoDB: In a MySQL replication slave the last"

		" master binlog file\n"

		"InnoDB: position %lu %lu, file name %s\n",

		(ulong) mach_read_from_4(sys_header

					 + TRX_SYS_MYSQL_MASTER_LOG_INFO

					 + TRX_SYS_MYSQL_LOG_OFFSET_HIGH),

		(ulong) mach_read_from_4(sys_header

					 + TRX_SYS_MYSQL_MASTER_LOG_INFO

					 + TRX_SYS_MYSQL_LOG_OFFSET_LOW),

		sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO

		+ TRX_SYS_MYSQL_LOG_NAME);

	/* Copy the master log position info to global variables we can

	use in ha_innobase.cc to initialize glob_mi to right values */

	ut_memcpy(trx_sys_mysql_master_log_name,

		  sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO

		  + TRX_SYS_MYSQL_LOG_NAME,

		  TRX_SYS_MYSQL_LOG_NAME_LEN);

	trx_sys_mysql_master_log_pos

		= (((ib_int64_t) mach_read_from_4(

			    sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO

			    + TRX_SYS_MYSQL_LOG_OFFSET_HIGH)) << 32)

		+ ((ib_int64_t) mach_read_from_4(

			   sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO

			   + TRX_SYS_MYSQL_LOG_OFFSET_LOW));

	mtr_commit(&mtr);

}

/****************************************************************//**

Looks for a free slot for a rollback segment in the trx system file copy.