branches/zip: Merge revisions 968:1009 from trunk.

buf/buf0buf.c

@@ -201,6 +201,9 @@ that the whole area may be needed in the near future, and issue
 the read requests for the whole area.
 */
 
+/* Value in microseconds */
+static const int WAIT_FOR_READ	= 20000;
+
 buf_pool_t*	buf_pool = NULL; /* The buffer buf_pool of the database */
 
 #ifdef UNIV_DEBUG
@@ -613,6 +616,8 @@ buf_block_init(
 #endif /* UNIV_DEBUG */
 	page_zip_des_init(&block->page_zip);
 
+	mutex_create(&block->mutex, SYNC_BUF_BLOCK);
+
 	rw_lock_create(&block->lock, SYNC_LEVEL_VARYING);
 	ut_ad(rw_lock_validate(&(block->lock)));
 
@@ -758,13 +763,22 @@ buf_block_make_young(
 /*=================*/
 	buf_block_t*	block)	/* in: block to make younger */
 {
+#ifdef UNIV_SYNC_DEBUG
+	ut_ad(!mutex_own(&(buf_pool->mutex)));
+#endif /* UNIV_SYNC_DEBUG */
+
+	/* Note that we read freed_page_clock's without holding any mutex:
+	this is allowed since the result is used only in heuristics */
+
 	if (buf_pool->freed_page_clock >= block->freed_page_clock
-	    + 1 + (buf_pool->curr_size / 1024)) {
+				+ 1 + (buf_pool->curr_size / 4)) {
 
+		mutex_enter(&buf_pool->mutex);
 		/* There has been freeing activity in the LRU list:
 		best to move to the head of the LRU list */
 
 		buf_LRU_make_block_young(block);
+		mutex_exit(&buf_pool->mutex);
 	}
 }
 
@@ -981,9 +995,8 @@ buf_page_get_gen(
 #endif
 	buf_pool->n_page_gets++;
 loop:
-	mutex_enter_fast(&(buf_pool->mutex));
-
 	block = NULL;
+	mutex_enter_fast(&(buf_pool->mutex));
 
 	if (guess) {
 		block = guess;
@@ -1021,6 +1034,8 @@ loop:
 		goto loop;
 	}
 
+	mutex_enter(&block->mutex);
+
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
 	must_read = FALSE;
@@ -1030,9 +1045,9 @@ loop:
 		must_read = TRUE;
 
 		if (mode == BUF_GET_IF_IN_POOL) {
-
 			/* The page is only being read to buffer */
-			mutex_exit(&(buf_pool->mutex));
+			mutex_exit(&buf_pool->mutex);
+			mutex_exit(&block->mutex);
 
 			return(NULL);
 		}
@@ -1043,7 +1058,7 @@ loop:
 #else
 	buf_block_buf_fix_inc(block);
 #endif
-	buf_block_make_young(block);
+	mutex_exit(&buf_pool->mutex);
 
 	/* Check if this is the first access to the page */
 
@@ -1051,10 +1066,13 @@ loop:
 
 	block->accessed = TRUE;
 
+	mutex_exit(&block->mutex);
+
+	buf_block_make_young(block);
+
 #ifdef UNIV_DEBUG_FILE_ACCESSES
 	ut_a(block->file_page_was_freed == FALSE);
 #endif
-	mutex_exit(&(buf_pool->mutex));
 
 #ifdef UNIV_DEBUG
 	buf_dbg_counter++;
@@ -1079,13 +1097,14 @@ loop:
 		}
 
 		if (!success) {
-			mutex_enter(&(buf_pool->mutex));
+			mutex_enter(&block->mutex);
 
 			block->buf_fix_count--;
+
+			mutex_exit(&block->mutex);
 #ifdef UNIV_SYNC_DEBUG
 			rw_lock_s_unlock(&(block->debug_latch));
 #endif
-			mutex_exit(&(buf_pool->mutex));
 
 			return(NULL);
 		}
@@ -1096,18 +1115,16 @@ loop:
 			completes */
 
 			for (;;) {
-				mutex_enter(&(buf_pool->mutex));
+				mutex_enter(&block->mutex);
 
 				if (block->io_fix == BUF_IO_READ) {
 
-					mutex_exit(&(buf_pool->mutex));
+					mutex_exit(&block->mutex);
 
-					/* Sleep 20 milliseconds */
-
-					os_thread_sleep(20000);
+					os_thread_sleep(WAIT_FOR_READ);
 				} else {
 
-					mutex_exit(&(buf_pool->mutex));
+					mutex_exit(&block->mutex);
 
 					break;
 				}
@@ -1165,11 +1182,11 @@ buf_page_optimistic_get_func(
 	ut_ad(mtr && block);
 	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));
 
-	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
 
 	if (UNIV_UNLIKELY(block->state != BUF_BLOCK_FILE_PAGE)) {
-exit_func:
-		mutex_exit(&(buf_pool->mutex));
+
+		mutex_exit(&block->mutex);
 
 		return(FALSE);
 	}
@@ -1179,15 +1196,14 @@ exit_func:
 #else
 	buf_block_buf_fix_inc(block);
 #endif
-	buf_block_make_young(block);
-
-	/* Check if this is the first access to the page */
-
 	accessed = block->accessed;
-
 	block->accessed = TRUE;
 
-	mutex_exit(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
+
+	buf_block_make_young(block);
+
+	/* Check if this is the first access to the page */
 
 	ut_ad(!ibuf_inside()
 	      || ibuf_page(block->space, buf_block_get_zip_size(block),
@@ -1204,13 +1220,16 @@ exit_func:
 	}
 
 	if (UNIV_UNLIKELY(!success)) {
-		mutex_enter(&(buf_pool->mutex));
+		mutex_enter(&block->mutex);
 
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
 #endif
-		goto exit_func;
+		return(FALSE);
 	}
 
 	if (UNIV_UNLIKELY(!UT_DULINT_EQ(modify_clock, block->modify_clock))) {
@@ -1223,13 +1242,16 @@ exit_func:
 			rw_lock_x_unlock(&(block->lock));
 		}
 
-		mutex_enter(&(buf_pool->mutex));
+		mutex_enter(&block->mutex);
 
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
 #endif
-		goto exit_func;
+		return(FALSE);
 	}
 
 	mtr_memo_push(mtr, block, fix_type);
@@ -1286,7 +1308,7 @@ buf_page_get_known_nowait(
 	ut_ad(mtr);
 	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));
 
-	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
 
 	if (block->state == BUF_BLOCK_REMOVE_HASH) {
 		/* Another thread is just freeing the block from the LRU list
@@ -1296,7 +1318,7 @@ buf_page_get_known_nowait(
 		we have already removed it from the page address hash table
 		of the buffer pool. */
 
-		mutex_exit(&(buf_pool->mutex));
+		mutex_exit(&block->mutex);
 
 		return(FALSE);
 	}
@@ -1308,12 +1330,12 @@ buf_page_get_known_nowait(
 #else
 	buf_block_buf_fix_inc(block);
 #endif
+	mutex_exit(&block->mutex);
+
 	if (mode == BUF_MAKE_YOUNG) {
 		buf_block_make_young(block);
 	}
 
-	mutex_exit(&(buf_pool->mutex));
-
 	ut_ad(!ibuf_inside() || (mode == BUF_KEEP_OLD));
 
 	if (rw_latch == RW_S_LATCH) {
@@ -1327,13 +1349,15 @@ buf_page_get_known_nowait(
 	}
 
 	if (!success) {
-		mutex_enter(&(buf_pool->mutex));
+		mutex_enter(&block->mutex);
 
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
 #endif
-		mutex_exit(&(buf_pool->mutex));
 
 		return(FALSE);
 	}
@@ -1384,7 +1408,6 @@ buf_page_init_for_backup_restore(
 	block->offset		= offset;
 
 	block->lock_hash_val	= 0;
-	block->lock_mutex	= NULL;
 
 	block->freed_page_clock = 0;
 
@@ -1424,6 +1447,7 @@ buf_page_init(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&(block->mutex)));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
 
@@ -1438,7 +1462,6 @@ buf_page_init(
 	block->index		= NULL;
 
 	block->lock_hash_val	= lock_rec_hash(space, offset);
-	block->lock_mutex	= NULL;
 
 	/* Insert into the hash table of file pages */
 
@@ -1533,6 +1556,7 @@ buf_page_init_for_read(
 	ut_a(block);
 
 	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
 
 	if (fil_tablespace_deleted_or_being_deleted_in_mem(
 		    space, tablespace_version)) {
@@ -1546,7 +1570,9 @@ buf_page_init_for_read(
 		    deleted or is being deleted, or the page is
 		    already in buf_pool, return */
 
+		mutex_exit(&block->mutex);
 		    mutex_exit(&(buf_pool->mutex));
+
 		    buf_block_free(block);
 
 		    if (mode == BUF_READ_IBUF_PAGES_ONLY) {
@@ -1566,6 +1592,7 @@ buf_page_init_for_read(
 	buf_LRU_add_block(block, TRUE);		/* TRUE == to old blocks */
 
 	block->io_fix = BUF_IO_READ;
+
 	buf_pool->n_pend_reads++;
 
 	/* We set a pass-type x-lock on the frame because then the same
@@ -1577,6 +1604,7 @@ buf_page_init_for_read(
 
 	rw_lock_x_lock_gen(&(block->lock), BUF_IO_READ);
 
+	mutex_exit(&block->mutex);
 	mutex_exit(&(buf_pool->mutex));
 
 	if (mode == BUF_READ_IBUF_PAGES_ONLY) {
@@ -1641,6 +1669,8 @@ buf_page_create(
 
 	block = free_block;
 
+	mutex_enter(&block->mutex);
+
 	buf_page_init(space, offset, block);
 
 	/* The block must be put to the LRU list */
@@ -1651,13 +1681,15 @@ buf_page_create(
 #else
 	buf_block_buf_fix_inc(block);
 #endif
+	buf_pool->n_pages_created++;
+
+	mutex_exit(&(buf_pool->mutex));
+
 	mtr_memo_push(mtr, block, MTR_MEMO_BUF_FIX);
 
 	block->accessed = TRUE;
 
-	buf_pool->n_pages_created++;
-
-	mutex_exit(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
 
 	/* Delete possible entries for the page from the insert buffer:
 	such can exist if the page belonged to an index which was dropped */
@@ -1709,6 +1741,12 @@ buf_page_io_complete(
 
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
+	/* We do not need protect block->io_fix here by block->mutex to read
+	it because this is the only function where we can change the value
+	from BUF_IO_READ or BUF_IO_WRITE to some other value, and our code
+	ensures that this is the only thread that handles the i/o for this
+	block. */
+
 	io_type = block->io_fix;
 
 	if (io_type == BUF_IO_READ) {
@@ -1848,11 +1886,12 @@ corrupt:
 		}
 	}
 
+	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
+
 #ifdef UNIV_IBUF_DEBUG
 	ut_a(ibuf_count_get(block->space, block->offset) == 0);
 #endif
-	mutex_enter(&(buf_pool->mutex));
-
 	/* Because this thread which does the unlocking is not the same that
 	did the locking, we use a pass value != 0 in unlock, which simply
 	removes the newest lock debug record, without checking the thread
@@ -1895,6 +1934,7 @@ corrupt:
 #endif /* UNIV_DEBUG */
 	}
 
+	mutex_exit(&block->mutex);
 	mutex_exit(&(buf_pool->mutex));
 
 #ifdef UNIV_DEBUG
@@ -1957,6 +1997,8 @@ buf_validate(void)
 
 		block = buf_pool_get_nth_block(buf_pool, i);
 
+		mutex_enter(&block->mutex);
+
 		if (block->state == BUF_BLOCK_FILE_PAGE) {
 
 			ut_a(buf_page_hash_get(block->space,
@@ -2001,6 +2043,8 @@ buf_validate(void)
 		} else if (block->state == BUF_BLOCK_NOT_USED) {
 			n_free++;
 		}
+
+		mutex_exit(&block->mutex);
 	}
 
 	if (n_lru + n_free > buf_pool->curr_size) {
@@ -2150,10 +2194,15 @@ buf_get_latched_pages_number(void)
 
 		block = buf_pool_get_nth_block(buf_pool, i);
 
-		if (((block->buf_fix_count != 0) || (block->io_fix != 0))
-		    && block->magic_n == BUF_BLOCK_MAGIC_N) {
+		if (block->magic_n == BUF_BLOCK_MAGIC_N) {
+			mutex_enter(&block->mutex);
+
+			if (block->buf_fix_count != 0 || block->io_fix != 0) {
 				fixed_pages_number++;
 			}
+
+			mutex_exit(&block->mutex);
+		}
 	}
 
 	mutex_exit(&(buf_pool->mutex));
@@ -2302,6 +2351,8 @@ buf_all_freed(void)
 
 		block = buf_pool_get_nth_block(buf_pool, i);
 
+		mutex_enter(&block->mutex);
+
 		if (block->state == BUF_BLOCK_FILE_PAGE) {
 
 			if (!buf_flush_ready_for_replace(block)) {
@@ -2313,6 +2364,8 @@ buf_all_freed(void)
 				ut_error;
 			}
 		}
+
+		mutex_exit(&block->mutex);
 	}
 
 	mutex_exit(&(buf_pool->mutex));

buf/buf0flu.c

@@ -114,6 +114,7 @@ buf_flush_ready_for_replace(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	if (block->state != BUF_BLOCK_FILE_PAGE) {
 		ut_print_timestamp(stderr);
@@ -149,6 +150,7 @@ buf_flush_ready_for_flush(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&(block->mutex)));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
@@ -635,8 +637,15 @@ buf_flush_try_page(
 
 	ut_a(!block || block->state == BUF_BLOCK_FILE_PAGE);
 
+	if (!block) {
+		mutex_exit(&(buf_pool->mutex));
+		return(0);
+	}
+
+	mutex_enter(&block->mutex);
+
 	if (flush_type == BUF_FLUSH_LIST
-	    && block && buf_flush_ready_for_flush(block, flush_type)) {
+	    && buf_flush_ready_for_flush(block, flush_type)) {
 
 		block->io_fix = BUF_IO_WRITE;
 
@@ -661,6 +670,7 @@ buf_flush_try_page(
 			locked = TRUE;
 		}
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		if (!locked) {
@@ -681,7 +691,7 @@ buf_flush_try_page(
 
 		return(1);
 
-	} else if (flush_type == BUF_FLUSH_LRU && block
+	} else if (flush_type == BUF_FLUSH_LRU
 		   && buf_flush_ready_for_flush(block, flush_type)) {
 
 		/* VERY IMPORTANT:
@@ -709,13 +719,14 @@ buf_flush_try_page(
 		buf_pool mutex: this ensures that the latch is acquired
 		immediately. */
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		buf_flush_write_block_low(block);
 
 		return(1);
 
-	} else if (flush_type == BUF_FLUSH_SINGLE_PAGE && block
+	} else if (flush_type == BUF_FLUSH_SINGLE_PAGE
 		   && buf_flush_ready_for_flush(block, flush_type)) {
 
 		block->io_fix = BUF_IO_WRITE;
@@ -729,6 +740,7 @@ buf_flush_try_page(
 
 		buf_pool->n_flush[flush_type]++;
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		rw_lock_s_lock_gen(&(block->lock), BUF_IO_WRITE);
@@ -746,11 +758,12 @@ buf_flush_try_page(
 		buf_flush_write_block_low(block);
 
 		return(1);
-	} else {
+	}
+
+	mutex_exit(&block->mutex);
 	mutex_exit(&(buf_pool->mutex));
 
 	return(0);
-	}
 }
 
 /***************************************************************
@@ -795,34 +808,48 @@ buf_flush_try_neighbors(
 		block = buf_page_hash_get(space, i);
 		ut_a(!block || block->state == BUF_BLOCK_FILE_PAGE);
 
-		if (block && flush_type == BUF_FLUSH_LRU && i != offset
+		if (!block) {
+
+			continue;
+
+		} else if (flush_type == BUF_FLUSH_LRU && i != offset
 			   && !block->old) {
 
 			/* We avoid flushing 'non-old' blocks in an LRU flush,
 			because the flushed blocks are soon freed */
 
 			continue;
-		}
+		} else {
 
-		if (block && buf_flush_ready_for_flush(block, flush_type)
+			mutex_enter(&block->mutex);
+
+			if (buf_flush_ready_for_flush(block, flush_type)
 			    && (i == offset || block->buf_fix_count == 0)) {
-			/* We only try to flush those neighbors != offset
-			where the buf fix count is zero, as we then know that
-			we probably can latch the page without a semaphore
-			wait. Semaphore waits are expensive because we must
+				/* We only try to flush those
+				neighbors != offset where the buf fix count is
+				zero, as we then know that we probably can
+				latch the page without a semaphore wait.
+				Semaphore waits are expensive because we must
 				flush the doublewrite buffer before we start
 				waiting. */
 
+				mutex_exit(&block->mutex);
+
 				mutex_exit(&(buf_pool->mutex));
 
-			/* Note: as we release the buf_pool mutex above, in
-			buf_flush_try_page we cannot be sure the page is still
-			in a flushable state: therefore we check it again
-			inside that function. */
+				/* Note: as we release the buf_pool mutex
+				above, in buf_flush_try_page we cannot be sure
+				the page is still in a flushable state:
+				therefore we check it again inside that
+				function. */
 
-			count += buf_flush_try_page(space, i, flush_type);
+				count += buf_flush_try_page(space, i,
+							    flush_type);
 
 				mutex_enter(&(buf_pool->mutex));
+			} else {
+				mutex_exit(&block->mutex);
+			}
 		}
 	}
 
@@ -918,12 +945,15 @@ buf_flush_batch(
 		while ((block != NULL) && !found) {
 			ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
+			mutex_enter(&block->mutex);
+
 			if (buf_flush_ready_for_flush(block, flush_type)) {
 
 				found = TRUE;
 				space = block->space;
 				offset = block->offset;
 
+				mutex_exit(&block->mutex);
 				mutex_exit(&(buf_pool->mutex));
 
 				old_page_count = page_count;
@@ -940,10 +970,14 @@ buf_flush_batch(
 
 			} else if (flush_type == BUF_FLUSH_LRU) {
 
+				mutex_exit(&block->mutex);
+
 				block = UT_LIST_GET_PREV(LRU, block);
 			} else {
 				ut_ad(flush_type == BUF_FLUSH_LIST);
 
+				mutex_exit(&block->mutex);
+
 				block = UT_LIST_GET_PREV(flush_list, block);
 			}
 		}
@@ -1026,10 +1060,14 @@ buf_flush_LRU_recommendation(void)
 		   + BUF_FLUSH_EXTRA_MARGIN)
 	       && (distance < BUF_LRU_FREE_SEARCH_LEN)) {
 
+		mutex_enter(&block->mutex);
+
 		if (buf_flush_ready_for_replace(block)) {
 			n_replaceable++;
 		}
 
+		mutex_exit(&block->mutex);
+
 		distance++;
 
 		block = UT_LIST_GET_PREV(LRU, block);

buf/buf0lru.c

@@ -86,6 +86,11 @@ scan_again:
 	block = UT_LIST_GET_LAST(buf_pool->LRU);
 
 	while (block != NULL) {
+		buf_block_t*	prev_block;
+
+		mutex_enter(&block->mutex);
+		prev_block = UT_LIST_GET_PREV(LRU, block);
+
 		ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
 		if (block->space == id
@@ -112,6 +117,8 @@ scan_again:
 			if (block->is_hashed) {
 				page_no = block->offset;
 
+				mutex_exit(&block->mutex);
+
 				mutex_exit(&(buf_pool->mutex));
 
 				/* Note that the following call will acquire
@@ -138,7 +145,8 @@ scan_again:
 			buf_LRU_block_free_hashed_page(block);
 		}
 next_page:
-		block = UT_LIST_GET_PREV(LRU, block);
+		mutex_exit(&block->mutex);
+		block = prev_block;
 	}
 
 	mutex_exit(&(buf_pool->mutex));
@@ -211,6 +219,9 @@ buf_LRU_search_and_free_block(
 
 	while (block != NULL) {
 		ut_a(block->in_LRU_list);
+
+		mutex_enter(&block->mutex);
+
 		if (buf_flush_ready_for_replace(block)) {
 
 #ifdef UNIV_DEBUG
@@ -226,20 +237,27 @@ buf_LRU_search_and_free_block(
 			buf_LRU_block_remove_hashed_page(block);
 
 			mutex_exit(&(buf_pool->mutex));
+			mutex_exit(&block->mutex);
 
 			/* Remove possible adaptive hash index on the page */
 
 			btr_search_drop_page_hash_index(block);
 
-			mutex_enter(&(buf_pool->mutex));
 
 			ut_a(block->buf_fix_count == 0);
 
+			mutex_enter(&(buf_pool->mutex));
+			mutex_enter(&block->mutex);
+
 			buf_LRU_block_free_hashed_page(block);
 			freed = TRUE;
+			mutex_exit(&block->mutex);
 
 			break;
 		}
+
+		mutex_exit(&block->mutex);
+
 		block = UT_LIST_GET_PREV(LRU, block);
 		distance++;
 
@@ -428,9 +446,13 @@ loop:
 			}
 		}
 
+		mutex_enter(&block->mutex);
+
 		block->state = BUF_BLOCK_READY_FOR_USE;
 		UNIV_MEM_VALID(block->frame, UNIV_PAGE_SIZE);
 
+		mutex_exit(&block->mutex);
+
 		mutex_exit(&(buf_pool->mutex));
 
 		if (started_monitor) {
@@ -816,6 +838,7 @@ buf_LRU_block_free_non_file_page(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_ad(block);
 
@@ -852,6 +875,7 @@ buf_LRU_block_remove_hashed_page(
 	const buf_block_t*	hashed_block;
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_ad(block);
 
@@ -911,6 +935,7 @@ buf_LRU_block_free_hashed_page(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state == BUF_BLOCK_REMOVE_HASH);
 

fil/fil0fil.c

@@ -4582,29 +4582,47 @@ fil_flush_file_spaces(
 {
 	fil_system_t*	system	= fil_system;
 	fil_space_t*	space;
+	ulint*		space_ids;
+	ulint		n_space_ids;
+	ulint		i;
 
 	mutex_enter(&(system->mutex));
 
-	space = UT_LIST_GET_FIRST(system->unflushed_spaces);
+	n_space_ids = UT_LIST_GET_LEN(system->unflushed_spaces);
+	if (n_space_ids == 0) {
 
-	while (space) {
-		if (space->purpose == purpose && !space->is_being_deleted) {
+		mutex_exit(&system->mutex);
+		return;
+	}
 
-			space->n_pending_flushes++; /* prevent dropping of
-						    the space while we are
-						    flushing */
-			mutex_exit(&(system->mutex));
+	/* Assemble a list of space ids to flush.  Previously, we
+	traversed system->unflushed_spaces and called UT_LIST_GET_NEXT()
+	on a space that was just removed from the list by fil_flush().
+	Thus, the space could be dropped and the memory overwritten. */
+	space_ids = mem_alloc(n_space_ids * sizeof *space_ids);
 
-			fil_flush(space->id);
+	n_space_ids = 0;
 
-			mutex_enter(&(system->mutex));
+	for (space = UT_LIST_GET_FIRST(system->unflushed_spaces);
+	     space;
+	     space = UT_LIST_GET_NEXT(unflushed_spaces, space)) {
 
-			space->n_pending_flushes--;
+		if (space->purpose == purpose && !space->is_being_deleted) {
+
+			space_ids[n_space_ids++] = space->id;
 		}
-		space = UT_LIST_GET_NEXT(unflushed_spaces, space);
 	}
 
-	mutex_exit(&(system->mutex));
+	mutex_exit(&system->mutex);
+
+	/* Flush the spaces.  It will not hurt to call fil_flush() on
+	a non-existing space id. */
+	for (i = 0; i < n_space_ids; i++) {
+
+		fil_flush(space_ids[i]);
+	}
+
+	mem_free(space_ids);
 }
 
 /**********************************************************************

handler/ha_innodb.cc

@@ -4433,7 +4433,7 @@ ha_innobase::rnd_pos(
 	}
 
 	if (error) {
-		DBUG_PRINT("error", ("Got error: %ld", error));
+		DBUG_PRINT("error", ("Got error: %d", error));
 		DBUG_RETURN(error);
 	}
 
@@ -4443,7 +4443,7 @@ ha_innobase::rnd_pos(
 	error = index_read(buf, pos, ref_length, HA_READ_KEY_EXACT);
 
 	if (error) {
-		DBUG_PRINT("error", ("Got error: %ld", error));
+		DBUG_PRINT("error", ("Got error: %d", error));
 	}
 
 	change_active_index(keynr);
@@ -5482,7 +5482,7 @@ ha_innobase::read_time(
 Returns statistics information of the table to the MySQL interpreter,
 in various fields of the handle object. */
 
-void
+int
 ha_innobase::info(
 /*==============*/
 	uint flag)	/* in: what information MySQL requests */
@@ -5505,7 +5505,7 @@ ha_innobase::info(
 
 	if (srv_force_recovery >= SRV_FORCE_NO_IBUF_MERGE) {
 
-		DBUG_VOID_RETURN;
+                DBUG_RETURN(HA_ERR_CRASHED);
 	}
 
 	/* We do not know if MySQL can call this function before calling
@@ -5697,7 +5697,7 @@ ha_innobase::info(
 
 	prebuilt->trx->op_info = (char*)"";
 
-	DBUG_VOID_RETURN;
+  	DBUG_RETURN(0);
 }
 
 /**************************************************************************

handler/ha_innodb.h

@@ -143,7 +143,7 @@ class ha_innobase: public handler
 	int rnd_pos(byte * buf, byte *pos);
 
 	void position(const byte *record);
-	void info(uint);
+	int info(uint);
 	int analyze(THD* thd,HA_CHECK_OPT* check_opt);
 	int optimize(THD* thd,HA_CHECK_OPT* check_opt);
 	int discard_or_import_tablespace(my_bool discard);

include/buf0buf.h

@@ -663,7 +663,10 @@ struct buf_block_struct{
 
 	ulint		magic_n;	/* magic number to check */
 	ulint		state;		/* state of the control block:
-					BUF_BLOCK_NOT_USED, ... */
+					BUF_BLOCK_NOT_USED, ...; changing
+					this is only allowed when a thread
+					has BOTH the buffer pool mutex AND
+					block->mutex locked */
 	byte*		frame;		/* pointer to buffer frame which
 					is of size UNIV_PAGE_SIZE, and
 					aligned to an address divisible by
@@ -672,8 +675,12 @@ struct buf_block_struct{
 	ulint		offset;		/* page number within the space */
 	ulint		lock_hash_val;	/* hashed value of the page address
 					in the record lock hash table */
-	mutex_t*	lock_mutex;	/* mutex protecting the chain in the
-					record lock hash table */
+	mutex_t		mutex;		/* mutex protecting this block:
+					state (also protected by the buffer
+					pool mutex), io_fix, buf_fix_count,
+					and accessed; we introduce this new
+					mutex in InnoDB-5.1 to relieve
+					contention on the buffer pool mutex */
 	rw_lock_t	lock;		/* read-write lock of the buffer
 					frame */
 	buf_block_t*	hash;		/* node used in chaining to the page
@@ -725,20 +732,27 @@ struct buf_block_struct{
 					in heuristic algorithms, because of
 					the possibility of a wrap-around! */
 	ulint		freed_page_clock;/* the value of freed_page_clock
-					buffer pool when this block was
-					last time put to the head of the
-					LRU list */
+					of the buffer pool when this block was
+					the last time put to the head of the
+					LRU list; a thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ibool		old;		/* TRUE if the block is in the old
 					blocks in the LRU list */
 	ibool		accessed;	/* TRUE if the page has been accessed
 					while in the buffer pool: read-ahead
 					may read in pages which have not been
-					accessed yet */
+					accessed yet; this is protected by
+					block->mutex; a thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ulint		buf_fix_count;	/* count of how manyfold this block
-					is currently bufferfixed */
+					is currently bufferfixed; this is
+					protected by block->mutex */
 	ulint		io_fix;		/* if a read is pending to the frame,
 					io_fix is BUF_IO_READ, in the case
-					of a write BUF_IO_WRITE, otherwise 0 */
+					of a write BUF_IO_WRITE, otherwise 0;
+					this is protected by block->mutex */
 	/* 4. Optimistic search field */
 
 	dulint		modify_clock;	/* this clock is incremented every
@@ -872,7 +886,9 @@ struct buf_pool_struct{
 					number of buffer blocks removed from
 					the end of the LRU list; NOTE that
 					this counter may wrap around at 4
-					billion! */
+					billion! A thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ulint		LRU_flush_ended;/* when an LRU flush ends for a page,
 					this is incremented by one; this is
 					set to zero when a buffer block is

include/buf0buf.ic

@@ -285,12 +285,16 @@ buf_block_free(
 /*===========*/
 	buf_block_t*	block)	/* in, own: block to be freed */
 {
-	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
-
 	mutex_enter(&(buf_pool->mutex));
 
+	mutex_enter(&block->mutex);
+
+	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
+
 	buf_LRU_block_free_non_file_page(block);
 
+	mutex_exit(&block->mutex);
+
 	mutex_exit(&(buf_pool->mutex));
 }
 
@@ -427,7 +431,7 @@ buf_block_buf_fix_inc_debug(
 
 	ret = rw_lock_s_lock_func_nowait(&(block->debug_latch), file, line);
 	ut_a(ret);
-
+	ut_a(mutex_own(&block->mutex));
 	block->buf_fix_count++;
 }
 #else /* UNIV_SYNC_DEBUG */
@@ -531,22 +535,23 @@ buf_page_release(
 {
 	ut_ad(block);
 
-	mutex_enter_fast(&(buf_pool->mutex));
-
 	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(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
 
 	if (rw_latch == RW_S_LATCH) {
 		rw_lock_s_unlock(&(block->lock));

include/univ.i

@@ -80,6 +80,7 @@ memory is read outside the allocated blocks. */
 #define UNIV_DEBUG_VALGRIND
 #define UNIV_DEBUG_PRINT
 #define UNIV_DEBUG
+#define UNIV_LIST_DEBUG
 #define UNIV_MEM_DEBUG
 #define UNIV_IBUF_DEBUG
 #define UNIV_SYNC_DEBUG

include/ut0lst.h

@@ -123,27 +123,36 @@ name, NODE1 and NODE2 are pointers to nodes. */
 	}\
 }\
 
+/* Invalidate the pointers in a list node. */
+#ifdef UNIV_LIST_DEBUG
+# define UT_LIST_REMOVE_CLEAR(NAME, N)		\
+((N)->NAME.prev = (N)->NAME.next = (void*) -1)
+#else
+# define UT_LIST_REMOVE_CLEAR(NAME, N) while (0)
+#endif
+
 /***********************************************************************
 Removes a node from a two-way linked list. BASE has to be the base node
 (not a pointer to it). N has to be the pointer to the node to be removed
 from the list. NAME is the list name. */
 
-#define UT_LIST_REMOVE(NAME, BASE, N)\
-{\
-	ut_ad(N);\
-	ut_a((BASE).count > 0);\
-	((BASE).count)--;\
-	if (((N)->NAME).next != NULL) {\
-		((((N)->NAME).next)->NAME).prev = ((N)->NAME).prev;\
-	} else {\
-		(BASE).end = ((N)->NAME).prev;\
-	}\
-	if (((N)->NAME).prev != NULL) {\
-		((((N)->NAME).prev)->NAME).next = ((N)->NAME).next;\
-	} else {\
-		(BASE).start = ((N)->NAME).next;\
-	}\
-}\
+#define UT_LIST_REMOVE(NAME, BASE, N)					\
+do {									\
+	ut_ad(N);							\
+	ut_a((BASE).count > 0);						\
+	((BASE).count)--;						\
+	if (((N)->NAME).next != NULL) {					\
+		((((N)->NAME).next)->NAME).prev = ((N)->NAME).prev;	\
+	} else {							\
+		(BASE).end = ((N)->NAME).prev;				\
+	}								\
+	if (((N)->NAME).prev != NULL) {					\
+		((((N)->NAME).prev)->NAME).next = ((N)->NAME).next;	\
+	} else {							\
+		(BASE).start = ((N)->NAME).next;			\
+	}								\
+	UT_LIST_REMOVE_CLEAR(NAME, N);					\
+} while (0)
 
 /************************************************************************
 Gets the next node in a two-way list. NAME is the name of the list

lock/lock0lock.c

@@ -4548,10 +4548,6 @@ loop:
 					trx->read_view->up_limit_id));
 		}
 
-		fprintf(file,
-			"Trx has approximately %lu row locks\n",
-			(ulong) lock_number_of_rows_locked(trx));
-
 		if (trx->que_state == TRX_QUE_LOCK_WAIT) {
 			fprintf(file,
 				"------- TRX HAS BEEN WAITING %lu SEC"

mysql-test/innodb_mysql.result

 SET SESSION STORAGE_ENGINE = InnoDB;
 drop table if exists t1,t2,t1m,t1i,t2m,t2i,t4;
-create table t1(f1 varchar(800) binary not null, key(f1))
-character set utf8 collate utf8_general_ci;
-Warnings:
-Warning	1071	Specified key was too long; max key length is 765 bytes
-insert into t1 values('aaa');
-drop table t1;
 create table t1 (
 c_id int(11) not null default '0',
 org_id int(11) default null,
@@ -111,6 +105,14 @@ SELECT `id1` FROM `t1` WHERE `id1` NOT IN (SELECT `id1` FROM `t2` WHERE `id2` =
 id1
 2
 DROP TABLE t1, t2;
+create table t1 (c1 int) engine=innodb;
+handler t1 open;
+handler t1 read first;
+c1
+Before and after comparison
+0
+drop table t1;
+End of 4.1 tests
 create table t1m (a int) engine = MEMORY;
 create table t1i (a int);
 create table t2m (a int) engine = MEMORY;
@@ -248,6 +250,22 @@ b
 c
 d
 drop table t1,t4;
+DROP TABLE IF EXISTS t2, t1;
+CREATE TABLE t1 (i INT NOT NULL PRIMARY KEY) ENGINE= InnoDB;
+CREATE TABLE t2 (
+i INT NOT NULL,
+FOREIGN KEY (i) REFERENCES t1 (i) ON DELETE NO ACTION
+) ENGINE= InnoDB;
+INSERT INTO t1 VALUES (1);
+INSERT INTO t2 VALUES (1);
+DELETE IGNORE FROM t1 WHERE i = 1;
+Warnings:
+Error	1451	Cannot delete or update a parent row: a foreign key constraint fails (`test`.`t2`, CONSTRAINT `t2_ibfk_1` FOREIGN KEY (`i`) REFERENCES `t1` (`i`) ON DELETE NO ACTION)
+SELECT * FROM t1, t2;
+i	i
+1	1
+DROP TABLE t2, t1;
+End of 4.1 tests.
 create table t1 (
 a varchar(30), b varchar(30), primary key(a), key(b)
 );
@@ -369,6 +387,23 @@ Warnings:
 Warning	1071	Specified key was too long; max key length is 765 bytes
 insert into t1 values('aaa');
 drop table t1;
+CREATE TABLE t1 (a INT PRIMARY KEY, b INT, c FLOAT, KEY b(b)) ENGINE = INNODB;
+INSERT INTO t1 VALUES (    1 , 1              , 1);
+INSERT INTO t1 SELECT  a + 1 , MOD(a + 1 , 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 2 , MOD(a + 2 , 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 4 , MOD(a + 4 , 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 8 , MOD(a + 8 , 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 16, MOD(a + 16, 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 32, MOD(a + 32, 20), 1 FROM t1;
+INSERT INTO t1 SELECT  a + 64, MOD(a + 64, 20), 1 FROM t1;
+EXPLAIN SELECT b, SUM(c) FROM t1 GROUP BY b;
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	SIMPLE	t1	index	NULL	b	5	NULL	128	
+EXPLAIN SELECT SQL_BIG_RESULT b, SUM(c) FROM t1 GROUP BY b;
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	SIMPLE	t1	ALL	NULL	NULL	NULL	NULL	128	Using filesort
+DROP TABLE t1;
+End of 5.0 tests
 CREATE TABLE `t2` (
 `k` int(11) NOT NULL auto_increment,
 `a` int(11) default NULL,
@@ -437,3 +472,4 @@ k	a	c
 11	15	1
 12	20	1
 drop table t2;
+End of 5.1 tests

plug.in

@@ -68,4 +68,5 @@ MYSQL_PLUGIN_ACTIONS(innobase,  [
       storage/innobase/handler/Makefile
       storage/innobase/usr/Makefile)
   ])
+MYSQL_PLUGIN_DEPENDS_ON_MYSQL_INTERNALS(innobase, [handler/ha_innodb.cc])
 

trx/trx0trx.c

@@ -1761,11 +1761,10 @@ trx_print(
 	    || mem_heap_get_size(trx->lock_heap) > 400) {
 		newline = TRUE;
 
-		fprintf(f, "%lu lock struct(s), heap size %lu",
+		fprintf(f, "%lu lock struct(s), heap size %lu,"
+			" %lu row lock(s)",
 			(ulong) UT_LIST_GET_LEN(trx->trx_locks),
-			(ulong) mem_heap_get_size(trx->lock_heap));
-
-		fprintf(f, "%lu row lock(s)",
+			(ulong) mem_heap_get_size(trx->lock_heap),
 			(ulong) lock_number_of_rows_locked(trx));
 	}