标签:
参考http://wqtn22.iteye.com/blog/1820436
http://blog.jcole.us/2013/01/10/btree-index-structures-in-innodb/
#define btr_pcur_open_on_user_rec(i,t,md,l,c,m) \ btr_pcur_open_on_user_rec_func(i,t,md,l,c,__FILE__,__LINE__,m)
/**************************************************************//** If mode is PAGE_CUR_G or PAGE_CUR_GE, opens a persistent cursor on the first user record satisfying the search condition, in the case PAGE_CUR_L or PAGE_CUR_LE, on the last user record. If no such user record exists, then in the first case sets the cursor after last in tree, and in the latter case before first in tree. The latching mode must be BTR_SEARCH_LEAF or BTR_MODIFY_LEAF. */ UNIV_INTERN void btr_pcur_open_on_user_rec_func( /*===========================*/ dict_index_t* index, /*!< in: index */ const dtuple_t* tuple, /*!< in: tuple on which search done */ ulint mode, /*!< in: PAGE_CUR_L, ... */ ulint latch_mode, /*!< in: BTR_SEARCH_LEAF or BTR_MODIFY_LEAF */ btr_pcur_t* cursor, /*!< in: memory buffer for persistent cursor */ const char* file, /*!< in: file name */ ulint line, /*!< in: line where called */ mtr_t* mtr) /*!< in: mtr */ { btr_pcur_open_func(index, tuple, mode, latch_mode, cursor, file, line, mtr); if ((mode == PAGE_CUR_GE) || (mode == PAGE_CUR_G)) { if (btr_pcur_is_after_last_on_page(cursor)) { btr_pcur_move_to_next_user_rec(cursor, mtr); } } else { ut_ad((mode == PAGE_CUR_LE) || (mode == PAGE_CUR_L)); /* Not implemented yet */ ut_error; } }
/**************************************************************//** Initializes and opens a persistent cursor to an index tree. It should be closed with btr_pcur_close. */ UNIV_INLINE void btr_pcur_open_func( /*===============*/ dict_index_t* index, /*!< in: index */ const dtuple_t* tuple, /*!< in: tuple on which search done */ ulint mode, /*!< in: PAGE_CUR_L, ...; NOTE that if the search is made using a unique prefix of a record, mode should be PAGE_CUR_LE, not PAGE_CUR_GE, as the latter may end up on the previous page from the record! */ ulint latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */ btr_pcur_t* cursor, /*!< in: memory buffer for persistent cursor */ const char* file, /*!< in: file name */ ulint line, /*!< in: line where called */ mtr_t* mtr) /*!< in: mtr */ { btr_cur_t* btr_cursor; /* Initialize the cursor */ btr_pcur_init(cursor); cursor->latch_mode = latch_mode; cursor->search_mode = mode; /* Search with the tree cursor */ btr_cursor = btr_pcur_get_btr_cur(cursor); btr_cur_search_to_nth_level(index, 0, tuple, mode, latch_mode, btr_cursor, 0, file, line, mtr); cursor->pos_state = BTR_PCUR_IS_POSITIONED; cursor->trx_if_known = NULL; }
/********************************************************************//** Searches an index tree and positions a tree cursor on a given level. NOTE: n_fields_cmp in tuple must be set so that it cannot be compared to node pointer page number fields on the upper levels of the tree! Note that if mode is PAGE_CUR_LE, which is used in inserts, then cursor->up_match and cursor->low_match both will have sensible values. If mode is PAGE_CUR_GE, then up_match will a have a sensible value. If mode is PAGE_CUR_LE , cursor is left at the place where an insert of the search tuple should be performed in the B-tree. InnoDB does an insert immediately after the cursor. Thus, the cursor may end up on a user record, or on a page infimum record. */ UNIV_INTERN void btr_cur_search_to_nth_level( /*========================*/ dict_index_t* index, /*!< in: index */ ulint level, /*!< in: the tree level of search */ const dtuple_t* tuple, /*!< in: data tuple; NOTE: n_fields_cmp in tuple must be set so that it cannot get compared to the node ptr page number field! */ ulint mode, /*!< in: PAGE_CUR_L, ...; Inserts should always be made using PAGE_CUR_LE to search the position! */ ulint latch_mode, /*!< in: BTR_SEARCH_LEAF, ..., ORed with at most one of BTR_INSERT, BTR_DELETE_MARK, BTR_DELETE, or BTR_ESTIMATE; cursor->left_block is used to store a pointer to the left neighbor page, in the cases BTR_SEARCH_PREV and BTR_MODIFY_PREV; NOTE that if has_search_latch is != 0, we maybe do not have a latch set on the cursor page, we assume the caller uses his search latch to protect the record! */ btr_cur_t* cursor, /*!< in/out: tree cursor; the cursor page is s- or x-latched, but see also above! */ ulint has_search_latch,/*!< in: info on the latch mode the caller currently has on btr_search_latch: RW_S_LATCH, or 0 */ const char* file, /*!< in: file name */ ulint line, /*!< in: line where called */ mtr_t* mtr) /*!< in: mtr */ { page_t* page; buf_block_t* block; ulint space; buf_block_t* guess; ulint height; ulint page_no; ulint up_match; ulint up_bytes; ulint low_match; ulint low_bytes; ulint savepoint; ulint rw_latch; ulint page_mode; ulint buf_mode; ulint estimate; ulint zip_size; page_cur_t* page_cursor; btr_op_t btr_op; ulint root_height = 0; /* remove warning */ #ifdef BTR_CUR_ADAPT btr_search_t* info; #endif mem_heap_t* heap = NULL; ulint offsets_[REC_OFFS_NORMAL_SIZE]; ulint* offsets = offsets_; rec_offs_init(offsets_); /* Currently, PAGE_CUR_LE is the only search mode used for searches ending to upper levels */ ut_ad(level == 0 || mode == PAGE_CUR_LE); ut_ad(dict_index_check_search_tuple(index, tuple)); ut_ad(!dict_index_is_ibuf(index) || ibuf_inside(mtr)); ut_ad(dtuple_check_typed(tuple)); ut_ad(index->page != FIL_NULL); UNIV_MEM_INVALID(&cursor->up_match, sizeof cursor->up_match); UNIV_MEM_INVALID(&cursor->up_bytes, sizeof cursor->up_bytes); UNIV_MEM_INVALID(&cursor->low_match, sizeof cursor->low_match); UNIV_MEM_INVALID(&cursor->low_bytes, sizeof cursor->low_bytes); #ifdef UNIV_DEBUG cursor->up_match = ULINT_UNDEFINED; cursor->low_match = ULINT_UNDEFINED; #endif /* These flags are mutually exclusive, they are lumped together with the latch mode for historical reasons. It‘s possible for none of the flags to be set. */ switch (UNIV_EXPECT(latch_mode & (BTR_INSERT | BTR_DELETE | BTR_DELETE_MARK), 0)) { case 0: btr_op = BTR_NO_OP; break; case BTR_INSERT: btr_op = (latch_mode & BTR_IGNORE_SEC_UNIQUE) ? BTR_INSERT_IGNORE_UNIQUE_OP : BTR_INSERT_OP; break; case BTR_DELETE: btr_op = BTR_DELETE_OP; ut_a(cursor->purge_node); break; case BTR_DELETE_MARK: btr_op = BTR_DELMARK_OP; break; default: /* only one of BTR_INSERT, BTR_DELETE, BTR_DELETE_MARK should be specified at a time */ ut_error; } /* Operations on the insert buffer tree cannot be buffered. */ ut_ad(btr_op == BTR_NO_OP || !dict_index_is_ibuf(index)); /* Operations on the clustered index cannot be buffered. */ ut_ad(btr_op == BTR_NO_OP || !dict_index_is_clust(index)); estimate = latch_mode & BTR_ESTIMATE; /* Turn the flags unrelated to the latch mode off. */ latch_mode &= ~(BTR_INSERT | BTR_DELETE_MARK | BTR_DELETE | BTR_ESTIMATE | BTR_IGNORE_SEC_UNIQUE); cursor->flag = BTR_CUR_BINARY; cursor->index = index; #ifndef BTR_CUR_ADAPT guess = NULL; #else info = btr_search_get_info(index); guess = info->root_guess; #ifdef BTR_CUR_HASH_ADAPT #ifdef UNIV_SEARCH_PERF_STAT info->n_searches++; #endif if (rw_lock_get_writer(&btr_search_latch) == RW_LOCK_NOT_LOCKED && latch_mode <= BTR_MODIFY_LEAF && info->last_hash_succ && !estimate #ifdef PAGE_CUR_LE_OR_EXTENDS && mode != PAGE_CUR_LE_OR_EXTENDS #endif /* PAGE_CUR_LE_OR_EXTENDS */ /* If !has_search_latch, we do a dirty read of btr_search_enabled below, and btr_search_guess_on_hash() will have to check it again. */ && UNIV_LIKELY(btr_search_enabled) && btr_search_guess_on_hash(index, info, tuple, mode, latch_mode, cursor, has_search_latch, mtr)) { /* Search using the hash index succeeded */ ut_ad(cursor->up_match != ULINT_UNDEFINED || mode != PAGE_CUR_GE); ut_ad(cursor->up_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE); ut_ad(cursor->low_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE); btr_cur_n_sea++; return; } #endif /* BTR_CUR_HASH_ADAPT */ #endif /* BTR_CUR_ADAPT */ btr_cur_n_non_sea++; /* If the hash search did not succeed, do binary search down the tree */ if (has_search_latch) { /* Release possible search latch to obey latching order */ rw_lock_s_unlock(&btr_search_latch); } /* Store the position of the tree latch we push to mtr so that we know how to release it when we have latched leaf node(s) */ savepoint = mtr_set_savepoint(mtr); if (latch_mode == BTR_MODIFY_TREE) { mtr_x_lock(dict_index_get_lock(index), mtr); } else if (latch_mode == BTR_CONT_MODIFY_TREE) { /* Do nothing */ ut_ad(mtr_memo_contains(mtr, dict_index_get_lock(index), MTR_MEMO_X_LOCK)); } else { mtr_s_lock(dict_index_get_lock(index), mtr); } page_cursor = btr_cur_get_page_cur(cursor); space = dict_index_get_space(index); page_no = dict_index_get_page(index); up_match = 0; up_bytes = 0; low_match = 0; low_bytes = 0; height = ULINT_UNDEFINED; /* We use these modified search modes on non-leaf levels of the B-tree. These let us end up in the right B-tree leaf. In that leaf we use the original search mode. */ switch (mode) { case PAGE_CUR_GE: page_mode = PAGE_CUR_L; break; case PAGE_CUR_G: page_mode = PAGE_CUR_LE; break; default: #ifdef PAGE_CUR_LE_OR_EXTENDS ut_ad(mode == PAGE_CUR_L || mode == PAGE_CUR_LE || mode == PAGE_CUR_LE_OR_EXTENDS); #else /* PAGE_CUR_LE_OR_EXTENDS */ ut_ad(mode == PAGE_CUR_L || mode == PAGE_CUR_LE); #endif /* PAGE_CUR_LE_OR_EXTENDS */ page_mode = mode; break; } /* Loop and search until we arrive at the desired level */ search_loop: buf_mode = BUF_GET; rw_latch = RW_NO_LATCH; if (height != 0) { /* We are about to fetch the root or a non-leaf page. */ } else if (latch_mode <= BTR_MODIFY_LEAF) { rw_latch = latch_mode; if (btr_op != BTR_NO_OP && ibuf_should_try(index, btr_op != BTR_INSERT_OP)) { /* Try to buffer the operation if the leaf page is not in the buffer pool. */ buf_mode = btr_op == BTR_DELETE_OP ? BUF_GET_IF_IN_POOL_OR_WATCH : BUF_GET_IF_IN_POOL; } } zip_size = dict_table_zip_size(index->table); retry_page_get: block = buf_page_get_gen( space, zip_size, page_no, rw_latch, guess, buf_mode, file, line, mtr); if (block == NULL) { /* This must be a search to perform an insert/delete mark/ delete; try using the insert/delete buffer */ ut_ad(height == 0); ut_ad(cursor->thr); switch (btr_op) { case BTR_INSERT_OP: case BTR_INSERT_IGNORE_UNIQUE_OP: ut_ad(buf_mode == BUF_GET_IF_IN_POOL); if (ibuf_insert(IBUF_OP_INSERT, tuple, index, space, zip_size, page_no, cursor->thr)) { cursor->flag = BTR_CUR_INSERT_TO_IBUF; goto func_exit; } break; case BTR_DELMARK_OP: ut_ad(buf_mode == BUF_GET_IF_IN_POOL); if (ibuf_insert(IBUF_OP_DELETE_MARK, tuple, index, space, zip_size, page_no, cursor->thr)) { cursor->flag = BTR_CUR_DEL_MARK_IBUF; goto func_exit; } break; case BTR_DELETE_OP: ut_ad(buf_mode == BUF_GET_IF_IN_POOL_OR_WATCH); if (!row_purge_poss_sec(cursor->purge_node, index, tuple)) { /* The record cannot be purged yet. */ cursor->flag = BTR_CUR_DELETE_REF; } else if (ibuf_insert(IBUF_OP_DELETE, tuple, index, space, zip_size, page_no, cursor->thr)) { /* The purge was buffered. */ cursor->flag = BTR_CUR_DELETE_IBUF; } else { /* The purge could not be buffered. */ buf_pool_watch_unset(space, page_no); break; } buf_pool_watch_unset(space, page_no); goto func_exit; default: ut_error; } /* Insert to the insert/delete buffer did not succeed, we must read the page from disk. */ buf_mode = BUF_GET; goto retry_page_get; } block->check_index_page_at_flush = TRUE; page = buf_block_get_frame(block); if (rw_latch != RW_NO_LATCH) { #ifdef UNIV_ZIP_DEBUG const page_zip_des_t* page_zip = buf_block_get_page_zip(block); ut_a(!page_zip || page_zip_validate(page_zip, page, index)); #endif /* UNIV_ZIP_DEBUG */ buf_block_dbg_add_level( block, dict_index_is_ibuf(index) ? SYNC_IBUF_TREE_NODE : SYNC_TREE_NODE); } ut_ad(index->id == btr_page_get_index_id(page)); if (UNIV_UNLIKELY(height == ULINT_UNDEFINED)) { /* We are in the root node */ height = btr_page_get_level(page, mtr); root_height = height; cursor->tree_height = root_height + 1; #ifdef BTR_CUR_ADAPT if (block != guess) { info->root_guess = block; } #endif } if (height == 0) { if (rw_latch == RW_NO_LATCH) { btr_cur_latch_leaves( page, space, zip_size, page_no, latch_mode, cursor, mtr); } if (latch_mode != BTR_MODIFY_TREE && latch_mode != BTR_CONT_MODIFY_TREE) { /* Release the tree s-latch */ mtr_release_s_latch_at_savepoint( mtr, savepoint, dict_index_get_lock(index)); } page_mode = mode; } page_cur_search_with_match( block, index, tuple, page_mode, &up_match, &up_bytes, &low_match, &low_bytes, page_cursor); if (estimate) { btr_cur_add_path_info(cursor, height, root_height); } /* If this is the desired level, leave the loop */ ut_ad(height == btr_page_get_level(page_cur_get_page(page_cursor), mtr)); if (level != height) { const rec_t* node_ptr; ut_ad(height > 0); height--; guess = NULL; node_ptr = page_cur_get_rec(page_cursor); offsets = rec_get_offsets( node_ptr, index, offsets, ULINT_UNDEFINED, &heap); /* Go to the child node */ page_no = btr_node_ptr_get_child_page_no(node_ptr, offsets); if (UNIV_UNLIKELY(height == 0 && dict_index_is_ibuf(index))) { /* We‘re doing a search on an ibuf tree and we‘re one level above the leaf page. */ ut_ad(level == 0); buf_mode = BUF_GET; rw_latch = RW_NO_LATCH; goto retry_page_get; } goto search_loop; } if (level != 0) { /* x-latch the page */ buf_block_t* child_block = btr_block_get( space, zip_size, page_no, RW_X_LATCH, index, mtr); page = buf_block_get_frame(child_block); btr_assert_not_corrupted(child_block, index); } else { cursor->low_match = low_match; cursor->low_bytes = low_bytes; cursor->up_match = up_match; cursor->up_bytes = up_bytes; #ifdef BTR_CUR_ADAPT /* We do a dirty read of btr_search_enabled here. We will properly check btr_search_enabled again in btr_search_build_page_hash_index() before building a page hash index, while holding btr_search_latch. */ if (UNIV_LIKELY(btr_search_enabled)) { btr_search_info_update(index, cursor); } #endif ut_ad(cursor->up_match != ULINT_UNDEFINED || mode != PAGE_CUR_GE); ut_ad(cursor->up_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE); ut_ad(cursor->low_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE); } func_exit: if (UNIV_LIKELY_NULL(heap)) { mem_heap_free(heap); } if (has_search_latch) { rw_lock_s_lock(&btr_search_latch); } }
/****************************************************************//** Searches the right position for a page cursor. */ UNIV_INTERN void page_cur_search_with_match( /*=======================*/ const buf_block_t* block, /*!< in: buffer block */ const dict_index_t* index, /*!< in: record descriptor */ const dtuple_t* tuple, /*!< in: data tuple */ ulint mode, /*!< in: PAGE_CUR_L, PAGE_CUR_LE, PAGE_CUR_G, or PAGE_CUR_GE */ ulint* iup_matched_fields, /*!< in/out: already matched fields in upper limit record */ ulint* iup_matched_bytes, /*!< in/out: already matched bytes in a field not yet completely matched */ ulint* ilow_matched_fields, /*!< in/out: already matched fields in lower limit record */ ulint* ilow_matched_bytes, /*!< in/out: already matched bytes in a field not yet completely matched */ page_cur_t* cursor) /*!< out: page cursor */ { ulint up; ulint low; ulint mid; const page_t* page; const page_dir_slot_t* slot; const rec_t* up_rec; const rec_t* low_rec; const rec_t* mid_rec; ulint up_matched_fields; ulint up_matched_bytes; ulint low_matched_fields; ulint low_matched_bytes; ulint cur_matched_fields; ulint cur_matched_bytes; int cmp; #ifdef UNIV_SEARCH_DEBUG int dbg_cmp; ulint dbg_matched_fields; ulint dbg_matched_bytes; #endif #ifdef UNIV_ZIP_DEBUG const page_zip_des_t* page_zip = buf_block_get_page_zip(block); #endif /* UNIV_ZIP_DEBUG */ mem_heap_t* heap = NULL; ulint offsets_[REC_OFFS_NORMAL_SIZE]; ulint* offsets = offsets_; rec_offs_init(offsets_); ut_ad(block && tuple && iup_matched_fields && iup_matched_bytes && ilow_matched_fields && ilow_matched_bytes && cursor); ut_ad(dtuple_validate(tuple)); #ifdef UNIV_DEBUG # ifdef PAGE_CUR_DBG if (mode != PAGE_CUR_DBG) # endif /* PAGE_CUR_DBG */ # ifdef PAGE_CUR_LE_OR_EXTENDS if (mode != PAGE_CUR_LE_OR_EXTENDS) # endif /* PAGE_CUR_LE_OR_EXTENDS */ ut_ad(mode == PAGE_CUR_L || mode == PAGE_CUR_LE || mode == PAGE_CUR_G || mode == PAGE_CUR_GE); #endif /* UNIV_DEBUG */ page = buf_block_get_frame(block); #ifdef UNIV_ZIP_DEBUG ut_a(!page_zip || page_zip_validate(page_zip, page, index)); #endif /* UNIV_ZIP_DEBUG */ page_check_dir(page); #ifdef PAGE_CUR_ADAPT if (page_is_leaf(page) && (mode == PAGE_CUR_LE) && (page_header_get_field(page, PAGE_N_DIRECTION) > 3) && (page_header_get_ptr(page, PAGE_LAST_INSERT)) && (page_header_get_field(page, PAGE_DIRECTION) == PAGE_RIGHT)) { if (page_cur_try_search_shortcut( block, index, tuple, iup_matched_fields, iup_matched_bytes, ilow_matched_fields, ilow_matched_bytes, cursor)) { return; } } # ifdef PAGE_CUR_DBG if (mode == PAGE_CUR_DBG) { mode = PAGE_CUR_LE; } # endif #endif /* The following flag does not work for non-latin1 char sets because cmp_full_field does not tell how many bytes matched */ #ifdef PAGE_CUR_LE_OR_EXTENDS ut_a(mode != PAGE_CUR_LE_OR_EXTENDS); #endif /* PAGE_CUR_LE_OR_EXTENDS */ /* If mode PAGE_CUR_G is specified, we are trying to position the cursor to answer a query of the form "tuple < X", where tuple is the input parameter, and X denotes an arbitrary physical record on the page. We want to position the cursor on the first X which satisfies the condition. */ up_matched_fields = *iup_matched_fields; up_matched_bytes = *iup_matched_bytes; low_matched_fields = *ilow_matched_fields; low_matched_bytes = *ilow_matched_bytes; /* Perform binary search. First the search is done through the page directory, after that as a linear search in the list of records owned by the upper limit directory slot. */ low = 0; up = page_dir_get_n_slots(page) - 1; /* Perform binary search until the lower and upper limit directory slots come to the distance 1 of each other */ while (up - low > 1) { mid = (low + up) / 2; slot = page_dir_get_nth_slot(page, mid); mid_rec = page_dir_slot_get_rec(slot); ut_pair_min(&cur_matched_fields, &cur_matched_bytes, low_matched_fields, low_matched_bytes, up_matched_fields, up_matched_bytes); offsets = rec_get_offsets(mid_rec, index, offsets, dtuple_get_n_fields_cmp(tuple), &heap); cmp = cmp_dtuple_rec_with_match(tuple, mid_rec, offsets, &cur_matched_fields, &cur_matched_bytes); if (UNIV_LIKELY(cmp > 0)) { low_slot_match: low = mid; low_matched_fields = cur_matched_fields; low_matched_bytes = cur_matched_bytes; } else if (UNIV_EXPECT(cmp, -1)) { #ifdef PAGE_CUR_LE_OR_EXTENDS if (mode == PAGE_CUR_LE_OR_EXTENDS && page_cur_rec_field_extends( tuple, mid_rec, offsets, cur_matched_fields)) { goto low_slot_match; } #endif /* PAGE_CUR_LE_OR_EXTENDS */ up_slot_match: up = mid; up_matched_fields = cur_matched_fields; up_matched_bytes = cur_matched_bytes; } else if (mode == PAGE_CUR_G || mode == PAGE_CUR_LE #ifdef PAGE_CUR_LE_OR_EXTENDS || mode == PAGE_CUR_LE_OR_EXTENDS #endif /* PAGE_CUR_LE_OR_EXTENDS */ ) { goto low_slot_match; } else { goto up_slot_match; } } slot = page_dir_get_nth_slot(page, low); low_rec = page_dir_slot_get_rec(slot); slot = page_dir_get_nth_slot(page, up); up_rec = page_dir_slot_get_rec(slot); /* Perform linear search until the upper and lower records come to distance 1 of each other. */ while (page_rec_get_next_const(low_rec) != up_rec) { mid_rec = page_rec_get_next_const(low_rec); ut_pair_min(&cur_matched_fields, &cur_matched_bytes, low_matched_fields, low_matched_bytes, up_matched_fields, up_matched_bytes); offsets = rec_get_offsets(mid_rec, index, offsets, dtuple_get_n_fields_cmp(tuple), &heap); cmp = cmp_dtuple_rec_with_match(tuple, mid_rec, offsets, &cur_matched_fields, &cur_matched_bytes); if (UNIV_LIKELY(cmp > 0)) { low_rec_match: low_rec = mid_rec; low_matched_fields = cur_matched_fields; low_matched_bytes = cur_matched_bytes; } else if (UNIV_EXPECT(cmp, -1)) { #ifdef PAGE_CUR_LE_OR_EXTENDS if (mode == PAGE_CUR_LE_OR_EXTENDS && page_cur_rec_field_extends( tuple, mid_rec, offsets, cur_matched_fields)) { goto low_rec_match; } #endif /* PAGE_CUR_LE_OR_EXTENDS */ up_rec_match: up_rec = mid_rec; up_matched_fields = cur_matched_fields; up_matched_bytes = cur_matched_bytes; } else if (mode == PAGE_CUR_G || mode == PAGE_CUR_LE #ifdef PAGE_CUR_LE_OR_EXTENDS || mode == PAGE_CUR_LE_OR_EXTENDS #endif /* PAGE_CUR_LE_OR_EXTENDS */ ) { goto low_rec_match; } else { goto up_rec_match; } } #ifdef UNIV_SEARCH_DEBUG /* Check that the lower and upper limit records have the right alphabetical order compared to tuple. */ dbg_matched_fields = 0; dbg_matched_bytes = 0; offsets = rec_get_offsets(low_rec, index, offsets, ULINT_UNDEFINED, &heap); dbg_cmp = page_cmp_dtuple_rec_with_match(tuple, low_rec, offsets, &dbg_matched_fields, &dbg_matched_bytes); if (mode == PAGE_CUR_G) { ut_a(dbg_cmp >= 0); } else if (mode == PAGE_CUR_GE) { ut_a(dbg_cmp == 1); } else if (mode == PAGE_CUR_L) { ut_a(dbg_cmp == 1); } else if (mode == PAGE_CUR_LE) { ut_a(dbg_cmp >= 0); } if (!page_rec_is_infimum(low_rec)) { ut_a(low_matched_fields == dbg_matched_fields); ut_a(low_matched_bytes == dbg_matched_bytes); } dbg_matched_fields = 0; dbg_matched_bytes = 0; offsets = rec_get_offsets(up_rec, index, offsets, ULINT_UNDEFINED, &heap); dbg_cmp = page_cmp_dtuple_rec_with_match(tuple, up_rec, offsets, &dbg_matched_fields, &dbg_matched_bytes); if (mode == PAGE_CUR_G) { ut_a(dbg_cmp == -1); } else if (mode == PAGE_CUR_GE) { ut_a(dbg_cmp <= 0); } else if (mode == PAGE_CUR_L) { ut_a(dbg_cmp <= 0); } else if (mode == PAGE_CUR_LE) { ut_a(dbg_cmp == -1); } if (!page_rec_is_supremum(up_rec)) { ut_a(up_matched_fields == dbg_matched_fields); ut_a(up_matched_bytes == dbg_matched_bytes); } #endif if (mode <= PAGE_CUR_GE) { page_cur_position(up_rec, block, cursor); } else { page_cur_position(low_rec, block, cursor); } *iup_matched_fields = up_matched_fields; *iup_matched_bytes = up_matched_bytes; *ilow_matched_fields = low_matched_fields; *ilow_matched_bytes = low_matched_bytes; if (UNIV_LIKELY_NULL(heap)) { mem_heap_free(heap); } }
/*************************************************************//** This function is used to compare a data tuple to a physical record. Only dtuple->n_fields_cmp first fields are taken into account for the data tuple! If we denote by n = n_fields_cmp, then rec must have either m >= n fields, or it must differ from dtuple in some of the m fields rec has. If rec has an externally stored field we do not compare it but return with value 0 if such a comparison should be made. @return 1, 0, -1, if dtuple is greater, equal, less than rec, respectively, when only the common first fields are compared, or until the first externally stored field in rec */ UNIV_INTERN int cmp_dtuple_rec_with_match( /*======================*/ const dtuple_t* dtuple, /*!< in: data tuple */ const rec_t* rec, /*!< in: physical record which differs from dtuple in some of the common fields, or which has an equal number or more fields than dtuple */ const ulint* offsets,/*!< in: array returned by rec_get_offsets() */ ulint* matched_fields, /*!< in/out: number of already completely matched fields; when function returns, contains the value for current comparison */ ulint* matched_bytes) /*!< in/out: number of already matched bytes within the first field not completely matched; when function returns, contains the value for current comparison */ { const dfield_t* dtuple_field; /* current field in logical record */ ulint dtuple_f_len; /* the length of the current field in the logical record */ const byte* dtuple_b_ptr; /* pointer to the current byte in logical field data */ ulint dtuple_byte; /* value of current byte to be compared in dtuple*/ ulint rec_f_len; /* length of current field in rec */ const byte* rec_b_ptr; /* pointer to the current byte in rec field */ ulint rec_byte; /* value of current byte to be compared in rec */ ulint cur_field; /* current field number */ ulint cur_bytes; /* number of already matched bytes in current field */ int ret = 3333; /* return value */ ut_ad(dtuple && rec && matched_fields && matched_bytes); ut_ad(dtuple_check_typed(dtuple)); ut_ad(rec_offs_validate(rec, NULL, offsets)); cur_field = *matched_fields; cur_bytes = *matched_bytes; ut_ad(cur_field <= dtuple_get_n_fields_cmp(dtuple)); ut_ad(cur_field <= rec_offs_n_fields(offsets)); if (cur_bytes == 0 && cur_field == 0) { ulint rec_info = rec_get_info_bits(rec, rec_offs_comp(offsets)); ulint tup_info = dtuple_get_info_bits(dtuple); if (UNIV_UNLIKELY(rec_info & REC_INFO_MIN_REC_FLAG)) { ret = !(tup_info & REC_INFO_MIN_REC_FLAG); goto order_resolved; } else if (UNIV_UNLIKELY(tup_info & REC_INFO_MIN_REC_FLAG)) { ret = -1; goto order_resolved; } } /* Match fields in a loop; stop if we run out of fields in dtuple or find an externally stored field */ while (cur_field < dtuple_get_n_fields_cmp(dtuple)) { ulint mtype; ulint prtype; dtuple_field = dtuple_get_nth_field(dtuple, cur_field); { const dtype_t* type = dfield_get_type(dtuple_field); mtype = type->mtype; prtype = type->prtype; } dtuple_f_len = dfield_get_len(dtuple_field); rec_b_ptr = rec_get_nth_field(rec, offsets, cur_field, &rec_f_len); /* If we have matched yet 0 bytes, it may be that one or both the fields are SQL null, or the record or dtuple may be the predefined minimum record, or the field is externally stored */ if (UNIV_LIKELY(cur_bytes == 0)) { if (rec_offs_nth_extern(offsets, cur_field)) { /* We do not compare to an externally stored field */ ret = 0; goto order_resolved; } if (dtuple_f_len == UNIV_SQL_NULL) { if (rec_f_len == UNIV_SQL_NULL) { goto next_field; } ret = -1; goto order_resolved; } else if (rec_f_len == UNIV_SQL_NULL) { /* We define the SQL null to be the smallest possible value of a field in the alphabetical order */ ret = 1; goto order_resolved; } } if (mtype >= DATA_FLOAT || (mtype == DATA_BLOB && 0 == (prtype & DATA_BINARY_TYPE) && dtype_get_charset_coll(prtype) != DATA_MYSQL_LATIN1_SWEDISH_CHARSET_COLL)) { ret = cmp_whole_field(mtype, prtype, dfield_get_data(dtuple_field), (unsigned) dtuple_f_len, rec_b_ptr, (unsigned) rec_f_len); if (ret != 0) { cur_bytes = 0; goto order_resolved; } else { goto next_field; } } /* Set the pointers at the current byte */ rec_b_ptr = rec_b_ptr + cur_bytes; dtuple_b_ptr = (byte*)dfield_get_data(dtuple_field) + cur_bytes; /* Compare then the fields */ for (;;) { if (UNIV_UNLIKELY(rec_f_len <= cur_bytes)) { if (dtuple_f_len <= cur_bytes) { goto next_field; } rec_byte = dtype_get_pad_char(mtype, prtype); if (rec_byte == ULINT_UNDEFINED) { ret = 1; goto order_resolved; } } else { rec_byte = *rec_b_ptr; } if (UNIV_UNLIKELY(dtuple_f_len <= cur_bytes)) { dtuple_byte = dtype_get_pad_char(mtype, prtype); if (dtuple_byte == ULINT_UNDEFINED) { ret = -1; goto order_resolved; } } else { dtuple_byte = *dtuple_b_ptr; } if (dtuple_byte == rec_byte) { /* If the bytes are equal, they will remain such even after the collation transformation below */ goto next_byte; } if (mtype <= DATA_CHAR || (mtype == DATA_BLOB && !(prtype & DATA_BINARY_TYPE))) { rec_byte = cmp_collate(rec_byte); dtuple_byte = cmp_collate(dtuple_byte); } ret = (int) (dtuple_byte - rec_byte); if (UNIV_LIKELY(ret)) { if (ret < 0) { ret = -1; goto order_resolved; } else { ret = 1; goto order_resolved; } } next_byte: /* Next byte */ cur_bytes++; rec_b_ptr++; dtuple_b_ptr++; } next_field: cur_field++; cur_bytes = 0; } ut_ad(cur_bytes == 0); ret = 0; /* If we ran out of fields, dtuple was equal to rec up to the common fields */ order_resolved: ut_ad((ret >= - 1) && (ret <= 1)); ut_ad(ret == cmp_debug_dtuple_rec_with_match(dtuple, rec, offsets, matched_fields)); ut_ad(*matched_fields == cur_field); /* In the debug version, the above cmp_debug_... sets *matched_fields to a value */ *matched_fields = cur_field; *matched_bytes = cur_bytes; return(ret); }
标签:
原文地址:http://www.cnblogs.com/taek/p/5052735.html