diff options
Diffstat (limited to 'innobase/row')
| -rw-r--r-- | innobase/row/row0ins.c | 25 | ||||
| -rw-r--r-- | innobase/row/row0sel.c | 8 | ||||
| -rw-r--r-- | innobase/row/row0umod.c | 124 | ||||
| -rw-r--r-- | innobase/row/row0upd.c | 86 | ||||
| -rw-r--r-- | innobase/row/row0vers.c | 27 |
5 files changed, 229 insertions, 41 deletions
diff --git a/innobase/row/row0ins.c b/innobase/row/row0ins.c index 1a7864be5e9..c89f41f69ad 100644 --- a/innobase/row/row0ins.c +++ b/innobase/row/row0ins.c @@ -225,11 +225,15 @@ ulint row_ins_sec_index_entry_by_modify( /*==============================*/ /* out: DB_SUCCESS or error code */ + ulint mode, /* in: BTR_MODIFY_LEAF or BTR_MODIFY_TREE, + depending on whether mtr holds just a leaf + latch or also a tree latch */ btr_cur_t* cursor, /* in: B-tree cursor */ dtuple_t* entry, /* in: index entry to insert */ que_thr_t* thr, /* in: query thread */ mtr_t* mtr) /* in: mtr */ { + big_rec_t* dummy_big_rec; mem_heap_t* heap; upd_t* update; rec_t* rec; @@ -241,16 +245,28 @@ row_ins_sec_index_entry_by_modify( ut_ad(rec_get_deleted_flag(rec)); /* We know that in the alphabetical ordering, entry and rec are - identical. But in their binary form there may be differences if + identified. But in their binary form there may be differences if there are char fields in them. Therefore we have to calculate the - difference and do an update-in-place if necessary. */ + difference. */ heap = mem_heap_create(1024); update = row_upd_build_sec_rec_difference_binary(cursor->index, entry, rec, heap); + if (mode == BTR_MODIFY_LEAF) { + /* Try an optimistic updating of the record, keeping changes + within the page */ - err = btr_cur_update_sec_rec_in_place(cursor, update, thr, mtr); + err = btr_cur_optimistic_update(BTR_KEEP_SYS_FLAG, cursor, + update, 0, thr, mtr); + if (err == DB_OVERFLOW || err == DB_UNDERFLOW) { + err = DB_FAIL; + } + } else { + ut_a(mode == BTR_MODIFY_TREE); + err = btr_cur_pessimistic_update(BTR_KEEP_SYS_FLAG, cursor, + &dummy_big_rec, update, 0, thr, mtr); + } mem_heap_free(heap); @@ -1838,7 +1854,8 @@ row_ins_index_entry_low( ext_vec, n_ext_vec, thr, &mtr); } else { - err = row_ins_sec_index_entry_by_modify(&cursor, entry, + err = row_ins_sec_index_entry_by_modify(mode, &cursor, + entry, thr, &mtr); } diff --git a/innobase/row/row0sel.c b/innobase/row/row0sel.c index f41574b2855..e6080a5f201 100644 --- a/innobase/row/row0sel.c +++ b/innobase/row/row0sel.c @@ -51,7 +51,8 @@ to que_run_threads: this is to allow canceling runaway queries */ /************************************************************************ Returns TRUE if the user-defined column values in a secondary index record -are the same as the corresponding columns in the clustered index record. +are alphabetically the same as the corresponding columns in the clustered +index record. NOTE: the comparison is NOT done as a binary comparison, but character fields are compared with collation! */ static @@ -96,11 +97,6 @@ row_sel_sec_rec_is_for_clust_rec( clust_len = ifield->prefix_len; } - if (sec_len != clust_len) { - - return(FALSE); - } - if (0 != cmp_data_data(dict_col_get_type(col), clust_field, clust_len, sec_field, sec_len)) { diff --git a/innobase/row/row0umod.c b/innobase/row/row0umod.c index 0a050e0a1b6..1bfd71f8c64 100644 --- a/innobase/row/row0umod.c +++ b/innobase/row/row0umod.c @@ -377,8 +377,14 @@ row_undo_mod_del_mark_or_remove_sec_low( } /*************************************************************** -Delete marks or removes a secondary index entry if found. */ -UNIV_INLINE +Delete marks or removes a secondary index entry if found. +NOTE that if we updated the fields of a delete-marked secondary index record +so that alphabetically they stayed the same, e.g., 'abc' -> 'aBc', we cannot +return to the original values because we do not know them. But this should +not cause problems because in row0sel.c, in queries we always retrieve the +clustered index record or an earlier version of it, if the secondary index +record through which we do the search is delete-marked. */ +static ulint row_undo_mod_del_mark_or_remove_sec( /*================================*/ @@ -403,20 +409,31 @@ row_undo_mod_del_mark_or_remove_sec( } /*************************************************************** -Delete unmarks a secondary index entry which must be found. */ +Delete unmarks a secondary index entry which must be found. It might not be +delete-marked at the moment, but it does not harm to unmark it anyway. We also +need to update the fields of the secondary index record if we updated its +fields but alphabetically they stayed the same, e.g., 'abc' -> 'aBc'. */ static -void -row_undo_mod_del_unmark_sec( -/*========================*/ +ulint +row_undo_mod_del_unmark_sec_and_undo_update( +/*========================================*/ + /* out: DB_FAIL or DB_SUCCESS or + DB_OUT_OF_FILE_SPACE */ + ulint mode, /* in: search mode: BTR_MODIFY_LEAF or + BTR_MODIFY_TREE */ undo_node_t* node, /* in: row undo node */ que_thr_t* thr, /* in: query thread */ dict_index_t* index, /* in: index */ dtuple_t* entry) /* in: index entry */ { + mem_heap_t* heap; btr_pcur_t pcur; btr_cur_t* btr_cur; - ulint err; + upd_t* update; + rec_t* rec; + ulint err = DB_SUCCESS; ibool found; + big_rec_t* dummy_big_rec; mtr_t mtr; char err_buf[1000]; @@ -425,8 +442,8 @@ row_undo_mod_del_unmark_sec( log_free_check(); mtr_start(&mtr); - found = row_search_index_entry(index, entry, BTR_MODIFY_LEAF, &pcur, - &mtr); + found = row_search_index_entry(index, entry, mode, &pcur, &mtr); + if (!found) { fprintf(stderr, "InnoDB: error in sec index entry del undo in\n" @@ -443,17 +460,47 @@ row_undo_mod_del_unmark_sec( "%s\nInnoDB: Make a detailed bug report and send it\n", err_buf); fprintf(stderr, "InnoDB: to mysql@lists.mysql.com\n"); - } else { btr_cur = btr_pcur_get_btr_cur(&pcur); + rec = btr_cur_get_rec(btr_cur); + err = btr_cur_del_mark_set_sec_rec(BTR_NO_LOCKING_FLAG, btr_cur, FALSE, thr, &mtr); - ut_ad(err == DB_SUCCESS); + ut_a(err == DB_SUCCESS); + heap = mem_heap_create(100); + + update = row_upd_build_sec_rec_difference_binary(index, entry, + rec, heap); + if (upd_get_n_fields(update) == 0) { + + /* Do nothing */ + + } else if (mode == BTR_MODIFY_LEAF) { + /* Try an optimistic updating of the record, keeping + changes within the page */ + + err = btr_cur_optimistic_update(BTR_KEEP_SYS_FLAG + | BTR_NO_LOCKING_FLAG, + btr_cur, update, 0, thr, &mtr); + if (err == DB_OVERFLOW || err == DB_UNDERFLOW) { + err = DB_FAIL; + } + } else { + ut_a(mode == BTR_MODIFY_TREE); + err = btr_cur_pessimistic_update(BTR_KEEP_SYS_FLAG + | BTR_NO_LOCKING_FLAG, + btr_cur, &dummy_big_rec, + update, 0, thr, &mtr); + } + + mem_heap_free(heap); } btr_pcur_close(&pcur); mtr_commit(&mtr); + + return(err); } /*************************************************************** @@ -501,13 +548,14 @@ static ulint row_undo_mod_del_mark_sec( /*======================*/ - /* out: DB_SUCCESS */ + /* out: DB_SUCCESS or DB_OUT_OF_FILE_SPACE */ undo_node_t* node, /* in: row undo node */ que_thr_t* thr) /* in: query thread */ { mem_heap_t* heap; dtuple_t* entry; dict_index_t* index; + ulint err; heap = mem_heap_create(1024); @@ -516,7 +564,21 @@ row_undo_mod_del_mark_sec( entry = row_build_index_entry(node->row, index, heap); - row_undo_mod_del_unmark_sec(node, thr, index, entry); + err = row_undo_mod_del_unmark_sec_and_undo_update( + BTR_MODIFY_LEAF, + node, thr, index, entry); + if (err == DB_FAIL) { + err = row_undo_mod_del_unmark_sec_and_undo_update( + BTR_MODIFY_TREE, + node, thr, index, entry); + } + + if (err != DB_SUCCESS) { + + mem_heap_free(heap); + + return(err); + } node->index = dict_table_get_next_index(node->index); } @@ -532,7 +594,7 @@ static ulint row_undo_mod_upd_exist_sec( /*=======================*/ - /* out: DB_SUCCESS or error code */ + /* out: DB_SUCCESS or DB_OUT_OF_FILE_SPACE */ undo_node_t* node, /* in: row undo node */ que_thr_t* thr) /* in: query thread */ { @@ -558,22 +620,48 @@ row_undo_mod_upd_exist_sec( /* Build the newest version of the index entry */ entry = row_build_index_entry(node->row, index, heap); + /* NOTE that if we updated the fields of a + delete-marked secondary index record so that + alphabetically they stayed the same, e.g., + 'abc' -> 'aBc', we cannot return to the original + values because we do not know them. But this should + not cause problems because in row0sel.c, in queries + we always retrieve the clustered index record or an + earlier version of it, if the secondary index record + through which we do the search is delete-marked. */ + err = row_undo_mod_del_mark_or_remove_sec(node, thr, - index, entry); + index, entry); if (err != DB_SUCCESS) { mem_heap_free(heap); return(err); } - + /* We may have to update the delete mark in the secondary index record of the previous version of - the row */ + the row. We also need to update the fields of + the secondary index record if we updated its fields + but alphabetically they stayed the same, e.g., + 'abc' -> 'aBc'. */ row_upd_index_replace_new_col_vals(entry, index, node->update, NULL); + err = row_undo_mod_del_unmark_sec_and_undo_update( + BTR_MODIFY_LEAF, + node, thr, index, entry); + if (err == DB_FAIL) { + err = + row_undo_mod_del_unmark_sec_and_undo_update( + BTR_MODIFY_TREE, + node, thr, index, entry); + } - row_undo_mod_del_unmark_sec(node, thr, index, entry); + if (err != DB_SUCCESS) { + mem_heap_free(heap); + + return(err); + } } node->index = dict_table_get_next_index(node->index); diff --git a/innobase/row/row0upd.c b/innobase/row/row0upd.c index 606f7404d50..b9e9b8c15c9 100644 --- a/innobase/row/row0upd.c +++ b/innobase/row/row0upd.c @@ -361,8 +361,8 @@ row_upd_changes_field_size_or_external( /* out: TRUE if the update changes the size of some field in index or the field is external in rec or update */ - rec_t* rec, /* in: record in clustered index */ - dict_index_t* index, /* in: clustered index */ + rec_t* rec, /* in: record in index */ + dict_index_t* index, /* in: index */ upd_t* update) /* in: update vector */ { upd_field_t* upd_field; @@ -372,8 +372,6 @@ row_upd_changes_field_size_or_external( ulint n_fields; ulint i; - ut_ad(index->type & DICT_CLUSTERED); - n_fields = upd_get_n_fields(update); for (i = 0; i < n_fields; i++) { @@ -698,7 +696,7 @@ row_upd_build_sec_rec_difference_binary( ulint i; /* This function is used only for a secondary index */ - ut_ad(0 == (index->type & DICT_CLUSTERED)); + ut_a(0 == (index->type & DICT_CLUSTERED)); update = upd_create(dtuple_get_n_fields(entry), heap); @@ -710,7 +708,13 @@ row_upd_build_sec_rec_difference_binary( dfield = dtuple_get_nth_field(entry, i); - ut_a(len == dfield_get_len(dfield)); + /* NOTE that it may be that len != dfield_get_len(dfield) if we + are updating in a character set and collation where strings of + different length can be equal in an alphabetical comparison, + and also in the case where we have a column prefix index + and the last characters in the index field are spaces; the + latter case probably caused the assertion failures reported at + row0upd.c line 713 in versions 4.0.14 - 4.0.16. */ /* NOTE: we compare the fields as binary strings! (No collation) */ @@ -820,12 +824,76 @@ Replaces the new column values stored in the update vector to the index entry given. */ void +row_upd_index_replace_new_col_vals_index_pos( +/*=========================================*/ + dtuple_t* entry, /* in/out: index entry where replaced */ + dict_index_t* index, /* in: index; NOTE that this may also be a + non-clustered index */ + upd_t* update, /* in: an update vector built for the index so + that the field number in an upd_field is the + index position */ + mem_heap_t* heap) /* in: memory heap to which we allocate and + copy the new values, set this as NULL if you + do not want allocation */ +{ + dict_field_t* field; + upd_field_t* upd_field; + dfield_t* dfield; + dfield_t* new_val; + ulint j; + ulint i; + + ut_ad(index); + + dtuple_set_info_bits(entry, update->info_bits); + + for (j = 0; j < dict_index_get_n_fields(index); j++) { + + field = dict_index_get_nth_field(index, j); + + for (i = 0; i < upd_get_n_fields(update); i++) { + + upd_field = upd_get_nth_field(update, i); + + if (upd_field->field_no == j) { + + dfield = dtuple_get_nth_field(entry, j); + + new_val = &(upd_field->new_val); + + dfield_set_data(dfield, new_val->data, + new_val->len); + if (heap && new_val->len != UNIV_SQL_NULL) { + dfield->data = mem_heap_alloc(heap, + new_val->len); + ut_memcpy(dfield->data, new_val->data, + new_val->len); + } + + if (field->prefix_len > 0 + && new_val->len != UNIV_SQL_NULL + && new_val->len > field->prefix_len) { + + dfield->len = field->prefix_len; + } + } + } + } +} + +/*************************************************************** +Replaces the new column values stored in the update vector to the index entry +given. */ + +void row_upd_index_replace_new_col_vals( /*===============================*/ dtuple_t* entry, /* in/out: index entry where replaced */ dict_index_t* index, /* in: index; NOTE that this may also be a non-clustered index */ - upd_t* update, /* in: update vector */ + upd_t* update, /* in: an update vector built for the + CLUSTERED index so that the field number in + an upd_field is the clustered index position */ mem_heap_t* heap) /* in: memory heap to which we allocate and copy the new values, set this as NULL if you do not want allocation */ @@ -893,7 +961,9 @@ row_upd_changes_ord_field_binary( known when this function is called, e.g., at compile time */ dict_index_t* index, /* in: index of the record */ - upd_t* update) /* in: update vector for the row */ + upd_t* update) /* in: update vector for the row; NOTE: the + field numbers in this MUST be clustered index + positions! */ { upd_field_t* upd_field; dict_field_t* ind_field; diff --git a/innobase/row/row0vers.c b/innobase/row/row0vers.c index d4a463d8a96..fca56389e45 100644 --- a/innobase/row/row0vers.c +++ b/innobase/row/row0vers.c @@ -117,9 +117,10 @@ row_vers_impl_x_locked_off_kernel( return(NULL); } - /* We look up if some earlier version of the clustered index record - would require rec to be in a different state (delete marked or - unmarked, or not existing). If there is such a version, then rec was + /* We look up if some earlier version, which was modified by the trx_id + transaction, of the clustered index record would require rec to be in + a different state (delete marked or unmarked, or have different field + values, or not existing). If there is such a version, then rec was modified by the trx_id transaction, and it has an implicit x-lock on rec. Note that if clust_rec itself would require rec to be in a different state, then the trx_id transaction has not yet had time to @@ -188,6 +189,8 @@ row_vers_impl_x_locked_off_kernel( vers_del = rec_get_deleted_flag(prev_version); + /* We check if entry and rec are identified in the alphabetical + ordering */ if (0 == cmp_dtuple_rec(entry, rec)) { /* The delete marks of rec and prev_version should be equal for rec to be in the state required by @@ -198,6 +201,20 @@ row_vers_impl_x_locked_off_kernel( break; } + + /* It is possible that the row was updated so that the + secondary index record remained the same in + alphabetical ordering, but the field values changed + still. For example, 'abc' -> 'ABC'. Check also that. */ + + dtuple_set_types_binary(entry, + dtuple_get_n_fields(entry)); + if (0 != cmp_dtuple_rec(entry, rec)) { + + trx = trx_get_on_id(trx_id); + + break; + } } else if (!rec_del) { /* The delete mark should be set in rec for it to be in the state required by prev_version */ @@ -256,8 +273,8 @@ row_vers_must_preserve_del_marked( Finds out if a version of the record, where the version >= the current purge view, should have ientry as its secondary index entry. We check if there is any not delete marked version of the record where the trx -id >= purge view, and the secondary index entry == ientry; exactly in -this case we return TRUE. */ +id >= purge view, and the secondary index entry and ientry are identified in +the alphabetical ordering; exactly in this case we return TRUE. */ ibool row_vers_old_has_index_entry( |