Skip to content

M
MariaDB
Commit d3d9b727 authored by heikki@hundin.mysql.fi's avatar heikki@hundin.mysql.fi
Browse files
Options

Many files: 

  Fix assertion failure on line 713 of row0upd.c if there is a column prefix index and the last characters in the prefix are spaces: do not assume that the length of alphabetically equal strings is the same; fix a buglet which could cause InnoDB to think that a secondary index record was not locked though it had been updated in a way which did not alpahabetically change its value, e.g., abc -> aBc
parent 9abb4be2
Show whitespace changes
Inline Side-by-side
Showing with 181 additions and 118 deletions
innobase/btr/btr0cur.c
View file @ d3d9b727
......@@ -1146,7 +1146,6 @@ btr_cur_pessimistic_insert(
}
/*==================== B-TREE UPDATE =========================*/
/* Only clustered index records are modified using these functions */
/*****************************************************************
For an update, checks the locks and does the undo logging. */
......@@ -1170,12 +1169,15 @@ btr_cur_upd_lock_and_undo(
ut_ad(cursor && update && thr && roll_ptr);
/* Only clustered index records are updated using this function */
ut_ad((cursor->index)->type & DICT_CLUSTERED);
rec = btr_cur_get_rec(cursor);
index = cursor->index;
if (!(index->type & DICT_CLUSTERED)) {
/* We do undo logging only when we update a clustered index
record */
return(lock_sec_rec_modify_check_and_lock(0, rec, index, thr));
}
/* Check if we have to wait for a lock: enqueue an explicit lock
request if yes */
......@@ -1222,6 +1224,13 @@ btr_cur_update_in_place_log(
mach_write_to_1(log_ptr, flags);
log_ptr++;
/* The code below assumes index is a clustered index: change index to
the clustered index if we are updating a secondary index record (or we
could as well skip writing the sys col values to the log in this case
because they are not needed for a secondary index record update) */
index = dict_table_get_first_index(index->table);
log_ptr = row_upd_write_sys_vals_to_log(index, trx, roll_ptr, log_ptr,
mtr);
mach_write_to_2(log_ptr, rec - buf_frame_align(rec));
......@@ -1308,68 +1317,7 @@ btr_cur_parse_update_in_place(
}
/*****************************************************************
Updates a secondary index record when the update causes no size
changes in its fields. The only case when this function is currently
called is that in a char field characters change to others which
are identified in the collation order. */
ulint
btr_cur_update_sec_rec_in_place(
/*============================*/
/* out: DB_SUCCESS or error number */
btr_cur_t* cursor, /* in: cursor on the record to update;
cursor stays valid and positioned on the
same record */
upd_t* update, /* in: update vector */
que_thr_t* thr, /* in: query thread */
mtr_t* mtr) /* in: mtr */
{
dict_index_t* index = cursor->index;
dict_index_t* clust_index;
ulint err;
rec_t* rec;
dulint roll_ptr = ut_dulint_zero;
trx_t* trx = thr_get_trx(thr);
/* Only secondary index records are updated using this function */
ut_ad(0 == (index->type & DICT_CLUSTERED));
rec = btr_cur_get_rec(cursor);
if (btr_cur_print_record_ops && thr) {
printf(
"Trx with id %lu %lu going to update table %s index %s\n",
ut_dulint_get_high(thr_get_trx(thr)->id),
ut_dulint_get_low(thr_get_trx(thr)->id),
index->table_name, index->name);
rec_print(rec);
}
err = lock_sec_rec_modify_check_and_lock(0, rec, index, thr);
if (err != DB_SUCCESS) {
return(err);
}
/* Remove possible hash index pointer to this record */
btr_search_update_hash_on_delete(cursor);
row_upd_rec_in_place(rec, update);
clust_index = dict_table_get_first_index(index->table);
/* Note that roll_ptr is really just a dummy value since
a secondary index record does not contain any sys columns */
btr_cur_update_in_place_log(BTR_KEEP_SYS_FLAG, rec, clust_index,
update, trx, roll_ptr, mtr);
return(DB_SUCCESS);
}
/*****************************************************************
Updates a record when the update causes no size changes in its fields.
We assume here that the ordering fields of the record do not change. */
Updates a record when the update causes no size changes in its fields. */
ulint
btr_cur_update_in_place(
......@@ -1389,13 +1337,10 @@ btr_cur_update_in_place(
buf_block_t* block;
ulint err;
rec_t* rec;
dulint roll_ptr;
dulint roll_ptr = ut_dulint_zero;
trx_t* trx;
ibool was_delete_marked;
/* Only clustered index records are updated using this function */
ut_ad(cursor->index->type & DICT_CLUSTERED);
rec = btr_cur_get_rec(cursor);
index = cursor->index;
trx = thr_get_trx(thr);
......@@ -1420,7 +1365,12 @@ btr_cur_update_in_place(
block = buf_block_align(rec);
if (block->is_hashed) {
if (row_upd_changes_ord_field_binary(NULL, index, update)) {
/* The function row_upd_changes_ord_field_binary works only
if the update vector was built for a clustered index, we must
NOT call it if index is secondary */
if (!(index->type & DICT_CLUSTERED)
|| row_upd_changes_ord_field_binary(NULL, index, update)) {
/* Remove possible hash index pointer to this record */
btr_search_update_hash_on_delete(cursor);
......@@ -1495,9 +1445,6 @@ btr_cur_optimistic_update(
ibool reorganized = FALSE;
ulint i;
/* Only clustered index records are updated using this function */
ut_ad((cursor->index)->type & DICT_CLUSTERED);
page = btr_cur_get_page(cursor);
rec = btr_cur_get_rec(cursor);
index = cursor->index;
......@@ -1546,8 +1493,8 @@ btr_cur_optimistic_update(
new_entry = row_rec_to_index_entry(ROW_COPY_DATA, index, rec, heap);
row_upd_index_replace_new_col_vals(new_entry, index, update, NULL);
row_upd_index_replace_new_col_vals_index_pos(new_entry, index, update,
NULL);
old_rec_size = rec_get_size(rec);
new_rec_size = rec_get_converted_size(new_entry);
......@@ -1729,7 +1676,6 @@ btr_cur_pessimistic_update(
index = cursor->index;
tree = index->tree;
ut_ad(index->type & DICT_CLUSTERED);
ut_ad(mtr_memo_contains(mtr, dict_tree_get_lock(tree),
MTR_MEMO_X_LOCK));
ut_ad(mtr_memo_contains(mtr, buf_block_align(page),
......@@ -1779,8 +1725,8 @@ btr_cur_pessimistic_update(
new_entry = row_rec_to_index_entry(ROW_COPY_DATA, index, rec, heap);
row_upd_index_replace_new_col_vals(new_entry, index, update, heap);
row_upd_index_replace_new_col_vals_index_pos(new_entry, index, update,
heap);
if (!(flags & BTR_KEEP_SYS_FLAG)) {
row_upd_index_entry_sys_field(new_entry, index, DATA_ROLL_PTR,
roll_ptr);
......
innobase/include/btr0cur.h
View file @ d3d9b727
......@@ -188,22 +188,6 @@ btr_cur_pessimistic_insert(
que_thr_t* thr, /* in: query thread or NULL */
mtr_t* mtr); /* in: mtr */
/*****************************************************************
Updates a secondary index record when the update causes no size
changes in its fields. The only case when this function is currently
called is that in a char field characters change to others which
are identified in the collation order. */
ulint
btr_cur_update_sec_rec_in_place(
/*============================*/
/* out: DB_SUCCESS or error number */
btr_cur_t* cursor, /* in: cursor on the record to update;
cursor stays valid and positioned on the
same record */
upd_t* update, /* in: update vector */
que_thr_t* thr, /* in: query thread */
mtr_t* mtr); /* in: mtr */
/*****************************************************************
Updates a record when the update causes no size changes in its fields. */
ulint
......
innobase/include/row0upd.h
View file @ d3d9b727
......@@ -171,13 +171,31 @@ row_upd_build_difference_binary(
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 */
/***************************************************************
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 may also be a
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 */
......@@ -199,7 +217,9 @@ 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! */
/***************************************************************
Checks if an update vector changes an ordering field of an index record.
This function is fast if the update vector is short or the number of ordering
......@@ -271,7 +291,10 @@ row_upd_index_parse(
/* Update vector field */
struct upd_field_struct{
ulint field_no; /* field number in the clustered
ulint field_no; /* field number in an index, usually
the clustered index, but in upadating
a secondary index record in btr0cur.c
this is the position in the secondary
index */
que_node_t* exp; /* expression for calculating a new
value: it refers to column values and
......
innobase/include/sync0sync.ic
View file @ d3d9b727
......@@ -257,6 +257,8 @@ mutex_enter_func(
mutex->file_name = file_name;
mutex->line = line;
mutex->thread_id = os_thread_get_curr_id();
return; /* Succeeded! */
}
......
innobase/lock/lock0lock.c
View file @ d3d9b727
......@@ -339,6 +339,11 @@ lock_deadlock_recursive(
ulint* cost); /* in/out: number of calculation steps thus
far: if this exceeds LOCK_MAX_N_STEPS_...
we return TRUE */
#define lock_mutex_enter_kernel() mutex_enter(&kernel_mutex)
#define lock_mutex_exit_kernel() mutex_exit(&kernel_mutex)
#ifdef notdefined
/*************************************************************************
Reserves the kernel mutex. This function is used in this module to allow
monitoring the contention degree on the kernel mutex caused by the lock
......@@ -362,6 +367,7 @@ lock_mutex_exit_kernel(void)
{
mutex_exit(&kernel_mutex);
}
#endif
#ifdef notdefined
......
innobase/row/row0ins.c
View file @ d3d9b727
......@@ -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);
......@@ -1829,7 +1845,8 @@ 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);
}
......
innobase/row/row0sel.c
View file @ d3d9b727
......@@ -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)) {
......
innobase/row/row0upd.c
View file @ d3d9b727
......@@ -698,7 +698,7 @@ 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 +710,13 @@ 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) */
......@@ -819,13 +825,77 @@ row_upd_build_difference_binary(
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 +963,9 @@ 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;
......
innobase/row/row0vers.c
View file @ d3d9b727
......@@ -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(
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7