~drizzle-trunk/drizzle/development

/******************************************************
The database buffer buf_pool

(c) 1995 Innobase Oy

Created 11/5/1995 Heikki Tuuri
*******************************************************/

#include "buf0flu.h"
#include "buf0lru.h"
#include "buf0rea.h"
#include "mtr0mtr.h"

#ifdef UNIV_DEBUG
extern ulint		buf_dbg_counter; /* This is used to insert validation
					operations in execution in the
					debug version */
#endif /* UNIV_DEBUG */
/************************************************************************
Recommends a move of a block to the start of the LRU list if there is danger
of dropping from the buffer pool. NOTE: does not reserve the buffer pool
mutex. */
UNIV_INLINE
ibool
buf_block_peek_if_too_old(
/*======================*/
				/* out: TRUE if should be made younger */
	buf_block_t*	block)	/* in: block to make younger */
{
	return(buf_pool->freed_page_clock >= block->freed_page_clock
	       + 1 + (buf_pool->curr_size / 4));
}

/*************************************************************************
Gets the current size of buffer buf_pool in bytes. In the case of AWE, the
size of AWE window (= the frames). */
UNIV_INLINE
ulint
buf_pool_get_curr_size(void)
/*========================*/
			/* out: size in bytes */
{
	return((buf_pool->n_frames) * UNIV_PAGE_SIZE);
}

/*************************************************************************
Gets the maximum size of buffer buf_pool in bytes. In the case of AWE, the
size of AWE window (= the frames). */
UNIV_INLINE
ulint
buf_pool_get_max_size(void)
/*=======================*/
			/* out: size in bytes */
{
	return((buf_pool->n_frames) * UNIV_PAGE_SIZE);
}

/***********************************************************************
Accessor function for block array. */
UNIV_INLINE
buf_block_t*
buf_pool_get_nth_block(
/*===================*/
				/* out: pointer to block */
	buf_pool_t*	buf_pool,/* in: buf_pool */
	ulint		i)	/* in: index of the block */
{
	ut_ad(buf_pool);
	ut_ad(i < buf_pool->max_size);

	return(i + buf_pool->blocks);
}

/***********************************************************************
Checks if a pointer points to the block array of the buffer pool (blocks, not
the frames). */
UNIV_INLINE
ibool
buf_pool_is_block(
/*==============*/
			/* out: TRUE if pointer to block */
	void*	ptr)	/* in: pointer to memory */
{
	if ((buf_pool->blocks <= (buf_block_t*)ptr)
	    && ((buf_block_t*)ptr < buf_pool->blocks
		+ buf_pool->max_size)) {

		return(TRUE);
	}

	return(FALSE);
}

/************************************************************************
Gets the smallest oldest_modification lsn for any page in the pool. Returns
ut_dulint_zero if all modified pages have been flushed to disk. */
UNIV_INLINE
dulint
buf_pool_get_oldest_modification(void)
/*==================================*/
				/* out: oldest modification in pool,
				ut_dulint_zero if none */
{
	buf_block_t*	block;
	dulint		lsn;

	mutex_enter(&(buf_pool->mutex));

	block = UT_LIST_GET_LAST(buf_pool->flush_list);

	if (block == NULL) {
		lsn = ut_dulint_zero;
	} else {
		lsn = block->oldest_modification;
	}

	mutex_exit(&(buf_pool->mutex));

	return(lsn);
}

/***********************************************************************
Increments the buf_pool clock by one and returns its new value. Remember
that in the 32 bit version the clock wraps around at 4 billion! */
UNIV_INLINE
ulint
buf_pool_clock_tic(void)
/*====================*/
			/* out: new clock value */
{
	ut_ad(mutex_own(&(buf_pool->mutex)));

	buf_pool->ulint_clock++;

	return(buf_pool->ulint_clock);
}

/*************************************************************************
Gets a pointer to the memory frame of a block. */
UNIV_INLINE
buf_frame_t*
buf_block_get_frame(
/*================*/
				/* out: pointer to the frame */
	buf_block_t*	block)	/* in: pointer to the control block */
{
	ut_ad(block);
	ut_ad(block >= buf_pool->blocks);
	ut_ad(block < buf_pool->blocks + buf_pool->max_size);
	ut_ad(block->state != BUF_BLOCK_NOT_USED);
	ut_ad((block->state != BUF_BLOCK_FILE_PAGE)
	      || (block->buf_fix_count > 0));

	return(block->frame);
}

/*************************************************************************
Gets the space id of a block. */
UNIV_INLINE
ulint
buf_block_get_space(
/*================*/
				/* out: space id */
	buf_block_t*	block)	/* in: pointer to the control block */
{
	ut_ad(block);
	ut_ad(block >= buf_pool->blocks);
	ut_ad(block < buf_pool->blocks + buf_pool->max_size);
	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
	ut_ad(block->buf_fix_count > 0);

	return(block->space);
}

/*************************************************************************
Gets the page number of a block. */
UNIV_INLINE
ulint
buf_block_get_page_no(
/*==================*/
				/* out: page number */
	buf_block_t*	block)	/* in: pointer to the control block */
{
	ut_ad(block);
	ut_ad(block >= buf_pool->blocks);
	ut_ad(block < buf_pool->blocks + buf_pool->max_size);
	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
	ut_ad(block->buf_fix_count > 0);

	return(block->offset);
}

/***********************************************************************
Gets the block to whose frame the pointer is pointing to. */
UNIV_INLINE
buf_block_t*
buf_block_align(
/*============*/
			/* out: pointer to block */
	byte*	ptr)	/* in: pointer to a frame */
{
	buf_block_t*	block;
	buf_frame_t*	frame_zero;

	ut_ad(ptr);

	frame_zero = buf_pool->frame_zero;

	if (UNIV_UNLIKELY((ulint)ptr < (ulint)frame_zero)
	    || UNIV_UNLIKELY((ulint)ptr > (ulint)(buf_pool->high_end))) {

		ut_print_timestamp(stderr);
		fprintf(stderr,
			"InnoDB: Error: trying to access a stray pointer %p\n"
			"InnoDB: buf pool start is at %p, end at %p\n"
			"InnoDB: Probable reason is database corruption"
			" or memory\n"
			"InnoDB: corruption. If this happens in an"
			" InnoDB database recovery, see\n"
			"InnoDB: http://dev.mysql.com/doc/refman/5.1/en/"
			"forcing-recovery.html\n"
			"InnoDB: how to force recovery.\n",
			ptr, frame_zero,
			buf_pool->high_end);
		ut_error;
	}

	block = *(buf_pool->blocks_of_frames + (((ulint)(ptr - frame_zero))
						>> UNIV_PAGE_SIZE_SHIFT));
	return(block);
}

/***********************************************************************
Gets the frame the pointer is pointing to. */
UNIV_INLINE
buf_frame_t*
buf_frame_align(
/*============*/
			/* out: pointer to frame */
	byte*	ptr)	/* in: pointer to a frame */
{
	buf_frame_t*	frame;

	ut_ad(ptr);

	frame = ut_align_down(ptr, UNIV_PAGE_SIZE);

	if (UNIV_UNLIKELY((ulint)frame < (ulint)(buf_pool->frame_zero))
	    || UNIV_UNLIKELY((ulint)frame >= (ulint)(buf_pool->high_end))) {

		ut_print_timestamp(stderr);
		fprintf(stderr,
			"InnoDB: Error: trying to access a stray pointer %p\n"
			"InnoDB: buf pool start is at %p, end at %p\n"
			"InnoDB: Probable reason is database corruption"
			" or memory\n"
			"InnoDB: corruption. If this happens in an"
			" InnoDB database recovery, see\n"
			"InnoDB: http://dev.mysql.com/doc/refman/5.1/en/"
			"forcing-recovery.html\n"
			"InnoDB: how to force recovery.\n",
			ptr, buf_pool->frame_zero,
			buf_pool->high_end);
		ut_error;
	}

	return(frame);
}

/**************************************************************************
Gets the page number of a pointer pointing within a buffer frame containing
a file page. */
UNIV_INLINE
ulint
buf_frame_get_page_no(
/*==================*/
			/* out: page number */
	byte*	ptr)	/* in: pointer to within a buffer frame */
{
	return(buf_block_get_page_no(buf_block_align(ptr)));
}

/**************************************************************************
Gets the space id of a pointer pointing within a buffer frame containing a
file page. */
UNIV_INLINE
ulint
buf_frame_get_space_id(
/*===================*/
			/* out: space id */
	byte*	ptr)	/* in: pointer to within a buffer frame */
{
	return(buf_block_get_space(buf_block_align(ptr)));
}

/**************************************************************************
Gets the space id, page offset, and byte offset within page of a
pointer pointing to a buffer frame containing a file page. */
UNIV_INLINE
void
buf_ptr_get_fsp_addr(
/*=================*/
	byte*		ptr,	/* in: pointer to a buffer frame */
	ulint*		space,	/* out: space id */
	fil_addr_t*	addr)	/* out: page offset and byte offset */
{
	buf_block_t*	block;

	block = buf_block_align(ptr);

	*space = buf_block_get_space(block);
	addr->page = buf_block_get_page_no(block);
	addr->boffset = ptr - buf_frame_align(ptr);
}

/**************************************************************************
Gets the hash value of the page the pointer is pointing to. This can be used
in searches in the lock hash table. */
UNIV_INLINE
ulint
buf_frame_get_lock_hash_val(
/*========================*/
			/* out: lock hash value */
	byte*	ptr)	/* in: pointer to within a buffer frame */
{
	buf_block_t*	block;

	block = buf_block_align(ptr);

	return(block->lock_hash_val);
}

/**************************************************************************
Gets the mutex number protecting the page record lock hash chain in the lock
table. */
UNIV_INLINE
mutex_t*
buf_frame_get_mutex(
/*================*/
			/* out: mutex */
	byte*	ptr)	/* in: pointer to within a buffer frame */
{
	buf_block_t*	block;

	block = buf_block_align(ptr);

	return(&block->mutex);
}

/*************************************************************************
Copies contents of a buffer frame to a given buffer. */
UNIV_INLINE
byte*
buf_frame_copy(
/*===========*/
				/* out: buf */
	byte*		buf,	/* in: buffer to copy to */
	buf_frame_t*	frame)	/* in: buffer frame */
{
	ut_ad(buf && frame);

	ut_memcpy(buf, frame, UNIV_PAGE_SIZE);

	return(buf);
}

/************************************************************************
Calculates a folded value of a file page address to use in the page hash
table. */
UNIV_INLINE
ulint
buf_page_address_fold(
/*==================*/
			/* out: the folded value */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: offset of the page within space */
{
	return((space << 20) + space + offset);
}

/************************************************************************
This function is used to get info if there is an io operation
going on on a buffer page. */
UNIV_INLINE
ibool
buf_page_io_query(
/*==============*/
				/* out: TRUE if io going on */
	buf_block_t*	block)	/* in: buf_pool block, must be bufferfixed */
{
	mutex_enter(&(buf_pool->mutex));

	ut_ad(block->state == BUF_BLOCK_FILE_PAGE);
	ut_ad(block->buf_fix_count > 0);

	if (block->io_fix != 0) {
		mutex_exit(&(buf_pool->mutex));

		return(TRUE);
	}

	mutex_exit(&(buf_pool->mutex));

	return(FALSE);
}

/************************************************************************
Gets the youngest modification log sequence number for a frame. Returns zero
if not a file page or no modification occurred yet. */
UNIV_INLINE
dulint
buf_frame_get_newest_modification(
/*==============================*/
				/* out: newest modification to the page */
	buf_frame_t*	frame)	/* in: pointer to a frame */
{
	buf_block_t*	block;
	dulint		lsn;

	ut_ad(frame);

	block = buf_block_align(frame);

	mutex_enter(&(buf_pool->mutex));

	if (block->state == BUF_BLOCK_FILE_PAGE) {
		lsn = block->newest_modification;
	} else {
		lsn = ut_dulint_zero;
	}

	mutex_exit(&(buf_pool->mutex));

	return(lsn);
}

/************************************************************************
Increments the modify clock of a frame by 1. The caller must (1) own the
buf_pool mutex and block bufferfix count has to be zero, (2) or own an x-lock
on the block. */
UNIV_INLINE
dulint
buf_frame_modify_clock_inc(
/*=======================*/
				/* out: new value */
	buf_frame_t*	frame)	/* in: pointer to a frame */
{
	buf_block_t*	block;

	ut_ad(frame);

	block = buf_block_align(frame);

#ifdef UNIV_SYNC_DEBUG
	ut_ad((mutex_own(&(buf_pool->mutex)) && (block->buf_fix_count == 0))
	      || rw_lock_own(&(block->lock), RW_LOCK_EXCLUSIVE));
#endif /* UNIV_SYNC_DEBUG */

	UT_DULINT_INC(block->modify_clock);

	return(block->modify_clock);
}

/************************************************************************
Increments the modify clock of a frame by 1. The caller must (1) own the
buf_pool mutex and block bufferfix count has to be zero, (2) or own an x-lock
on the block. */
UNIV_INLINE
dulint
buf_block_modify_clock_inc(
/*=======================*/
				/* out: new value */
	buf_block_t*	block)	/* in: block */
{
#ifdef UNIV_SYNC_DEBUG
	ut_ad((mutex_own(&(buf_pool->mutex)) && (block->buf_fix_count == 0))
	      || rw_lock_own(&(block->lock), RW_LOCK_EXCLUSIVE));
#endif /* UNIV_SYNC_DEBUG */

	UT_DULINT_INC(block->modify_clock);

	return(block->modify_clock);
}

/************************************************************************
Returns the value of the modify clock. The caller must have an s-lock
or x-lock on the block. */
UNIV_INLINE
dulint
buf_block_get_modify_clock(
/*=======================*/
				/* out: value */
	buf_block_t*	block)	/* in: block */
{
#ifdef UNIV_SYNC_DEBUG
	ut_ad(rw_lock_own(&(block->lock), RW_LOCK_SHARED)
	      || rw_lock_own(&(block->lock), RW_LOCK_EXCLUSIVE));
#endif /* UNIV_SYNC_DEBUG */

	return(block->modify_clock);
}

#ifdef UNIV_SYNC_DEBUG
/***********************************************************************
Increments the bufferfix count. */
UNIV_INLINE
void
buf_block_buf_fix_inc_debug(
/*========================*/
	buf_block_t*	block,	/* in: block to bufferfix */
	const char*	file __attribute__ ((unused)),	/* in: file name */
	ulint		line __attribute__ ((unused)))	/* in: line */
{
	ibool	ret;

	ret = rw_lock_s_lock_func_nowait(&(block->debug_latch), file, line);

	ut_ad(ret == TRUE);
	ut_ad(mutex_own(&block->mutex));
	block->buf_fix_count++;
}
#else /* UNIV_SYNC_DEBUG */
/***********************************************************************
Increments the bufferfix count. */
UNIV_INLINE
void
buf_block_buf_fix_inc(
/*==================*/
	buf_block_t*	block)	/* in: block to bufferfix */
{
	ut_ad(mutex_own(&block->mutex));

	block->buf_fix_count++;
}
#endif /* UNIV_SYNC_DEBUG */
/**********************************************************************
Returns the control block of a file page, NULL if not found. */
UNIV_INLINE
buf_block_t*
buf_page_hash_get(
/*==============*/
			/* out: block, NULL if not found */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: offset of the page within space */
{
	buf_block_t*	block;
	ulint		fold;

	ut_ad(buf_pool);
	ut_ad(mutex_own(&(buf_pool->mutex)));

	/* Look for the page in the hash table */

	fold = buf_page_address_fold(space, offset);

	HASH_SEARCH(hash, buf_pool->page_hash, fold, block,
		    (block->space == space) && (block->offset == offset));
	ut_a(block == NULL || block->state == BUF_BLOCK_FILE_PAGE);

	return(block);
}

/************************************************************************
Tries to get the page, but if file io is required, releases all latches
in mtr down to the given savepoint. If io is required, this function
retrieves the page to buffer buf_pool, but does not bufferfix it or latch
it. */
UNIV_INLINE
buf_frame_t*
buf_page_get_release_on_io(
/*=======================*/
				/* out: pointer to the frame, or NULL
				if not in buffer buf_pool */
	ulint	space,		/* in: space id */
	ulint	offset,		/* in: offset of the page within space
				in units of a page */
	buf_frame_t* guess,	/* in: guessed frame or NULL */
	ulint	rw_latch,	/* in: RW_X_LATCH, RW_S_LATCH,
				or RW_NO_LATCH */
	ulint	savepoint,	/* in: mtr savepoint */
	mtr_t*	mtr)		/* in: mtr */
{
	buf_frame_t*	frame;

	frame = buf_page_get_gen(space, offset, rw_latch, guess,
				 BUF_GET_IF_IN_POOL,
				 __FILE__, __LINE__,
				 mtr);
	if (frame != NULL) {

		return(frame);
	}

	/* The page was not in the buffer buf_pool: release the latches
	down to the savepoint */

	mtr_rollback_to_savepoint(mtr, savepoint);

	buf_page_get(space, offset, RW_S_LATCH, mtr);

	/* When we get here, the page is in buffer, but we release
	the latches again down to the savepoint, before returning */

	mtr_rollback_to_savepoint(mtr, savepoint);

	return(NULL);
}

/************************************************************************
Decrements the bufferfix count of a buffer control block and releases
a latch, if specified. */
UNIV_INLINE
void
buf_page_release(
/*=============*/
	buf_block_t*	block,		/* in: buffer block */
	ulint		rw_latch,	/* in: RW_S_LATCH, RW_X_LATCH,
					RW_NO_LATCH */
	mtr_t*		mtr)		/* in: mtr */
{
	ut_ad(block);

	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
	ut_a(block->buf_fix_count > 0);

	if (rw_latch == RW_X_LATCH && mtr->modifications) {
		mutex_enter(&buf_pool->mutex);
		buf_flush_note_modification(block, mtr);
		mutex_exit(&buf_pool->mutex);
	}

	mutex_enter(&block->mutex);

#ifdef UNIV_SYNC_DEBUG
	rw_lock_s_unlock(&(block->debug_latch));
#endif
	block->buf_fix_count--;

	mutex_exit(&block->mutex);

	if (rw_latch == RW_S_LATCH) {
		rw_lock_s_unlock(&(block->lock));
	} else if (rw_latch == RW_X_LATCH) {
		rw_lock_x_unlock(&(block->lock));
	}
}

#ifdef UNIV_SYNC_DEBUG
/*************************************************************************
Adds latch level info for the rw-lock protecting the buffer frame. This
should be called in the debug version after a successful latching of a
page if we know the latching order level of the acquired latch. If
UNIV_SYNC_DEBUG is not defined, compiles to an empty function. */
UNIV_INLINE
void
buf_page_dbg_add_level(
/*===================*/
	buf_frame_t*	frame __attribute__((unused)), /* in: buffer page
				where we have acquired latch */
	ulint		level __attribute__((unused))) /* in: latching order
				level */
{
	sync_thread_add_level(&(buf_block_align(frame)->lock), level);
}
#endif /* UNIV_SYNC_DEBUG */