/*************************************************************//**
Validates a given range of the cells in hash table.
@return TRUE if ok */
UNIV_INTERN
ibool
ha_validate(
/*========*/
hash_table_t* table, /*!< in: hash table */
ulint start_index, /*!< in: start index */
ulint end_index) /*!< in: end index */
{
hash_cell_t* cell;
ha_node_t* node;
ibool ok = TRUE;
ulint i;
ut_ad(table);
ut_ad(table->magic_n == HASH_TABLE_MAGIC_N);
ut_a(start_index <= end_index);
ut_a(start_index < hash_get_n_cells(table));
ut_a(end_index < hash_get_n_cells(table));
for (i = start_index; i <= end_index; i++) {
cell = hash_get_nth_cell(table, i);
node = cell->node;
while (node) {
if (hash_calc_hash(node->fold, table) != i) {
ut_print_timestamp(stderr);
fprintf(stderr,
"InnoDB: Error: hash table node"
" fold value %lu does not\n"
"InnoDB: match the cell number %lu.\n",
(ulong) node->fold, (ulong) i);
ok = FALSE;
}
node = node->next;
}
}
return(ok);
}
/********************************************************************//**
Issues read requests for pages which recovery wants to read in. */
UNIV_INTERN
void
buf_read_recv_pages(
/*================*/
ibool sync, /*!< in: TRUE if the caller
wants this function to wait
for the highest address page
to get read in, before this
function returns */
ulint space, /*!< in: space id */
ulint zip_size, /*!< in: compressed page size in
bytes, or 0 */
const ulint* page_nos, /*!< in: array of page numbers
to read, with the highest page
number the last in the
array */
ulint n_stored) /*!< in: number of page numbers
in the array */
{
ib_int64_t tablespace_version;
ulint count;
ulint err;
ulint i;
zip_size = fil_space_get_zip_size(space);
if (UNIV_UNLIKELY(zip_size == ULINT_UNDEFINED)) {
/* It is a single table tablespace and the .ibd file is
missing: do nothing */
/* the log records should be treated here same reason
for http://bugs.mysql.com/bug.php?id=43948 */
if (recv_recovery_is_on()) {
recv_addr_t* recv_addr;
mutex_enter(&(recv_sys->mutex));
if (recv_sys->apply_log_recs == FALSE) {
mutex_exit(&(recv_sys->mutex));
goto not_to_recover;
}
for (i = 0; i < n_stored; i++) {
/* recv_get_fil_addr_struct() */
recv_addr = HASH_GET_FIRST(recv_sys->addr_hash,
hash_calc_hash(ut_fold_ulint_pair(space, page_nos[i]),
recv_sys->addr_hash));
while (recv_addr) {
if ((recv_addr->space == space)
&& (recv_addr->page_no == page_nos[i])) {
break;
}
recv_addr = HASH_GET_NEXT(addr_hash, recv_addr);
}
if ((recv_addr == NULL)
|| (recv_addr->state == RECV_BEING_PROCESSED)
|| (recv_addr->state == RECV_PROCESSED)) {
continue;
}
recv_addr->state = RECV_PROCESSED;
ut_a(recv_sys->n_addrs);
recv_sys->n_addrs--;
}
mutex_exit(&(recv_sys->mutex));
fprintf(stderr, " (cannot find space: %lu)", space);
}
not_to_recover:
return;
}
tablespace_version = fil_space_get_version(space);
for (i = 0; i < n_stored; i++) {
buf_pool_t* buf_pool;
count = 0;
os_aio_print_debug = FALSE;
buf_pool = buf_pool_get(space, page_nos[i]);
while (buf_pool->n_pend_reads >= recv_n_pool_free_frames / 2) {
os_aio_simulated_wake_handler_threads();
os_thread_sleep(10000);
count++;
if (count > 1000) {
fprintf(stderr,
"InnoDB: Error: InnoDB has waited for"
" 10 seconds for pending\n"
"InnoDB: reads to the buffer pool to"
" be finished.\n"
"InnoDB: Number of pending reads %lu,"
" pending pread calls %lu\n",
(ulong) buf_pool->n_pend_reads,
(ulong)os_file_n_pending_preads);
os_aio_print_debug = TRUE;
}
}
os_aio_print_debug = FALSE;
if ((i + 1 == n_stored) && sync) {
buf_read_page_low(&err, TRUE, BUF_READ_ANY_PAGE, space,
zip_size, TRUE, tablespace_version,
page_nos[i], NULL);
} else {
buf_read_page_low(&err, FALSE, BUF_READ_ANY_PAGE
| OS_AIO_SIMULATED_WAKE_LATER,
space, zip_size, TRUE,
tablespace_version, page_nos[i], NULL);
}
}
os_aio_simulated_wake_handler_threads();
/* Flush pages from the end of all the LRU lists if necessary */
buf_flush_free_margins(FALSE);
#ifdef UNIV_DEBUG
if (buf_debug_prints) {
fprintf(stderr,
"Recovery applies read-ahead pages %lu\n",
(ulong) n_stored);
}
#endif /* UNIV_DEBUG */
}
/********************************************************************//**
Low-level function which reads a page asynchronously from a file to the
buffer buf_pool if it is not already there, in which case does nothing.
Sets the io_fix flag and sets an exclusive lock on the buffer frame. The
flag is cleared and the x-lock released by an i/o-handler thread.
@return 1 if a read request was queued, 0 if the page already resided
in buf_pool, or if the page is in the doublewrite buffer blocks in
which case it is never read into the pool, or if the tablespace does
not exist or is being dropped
@return 1 if read request is issued. 0 if it is not */
UNIV_INTERN
ulint
buf_read_page_low(
/*==============*/
ulint* err, /*!< out: DB_SUCCESS or DB_TABLESPACE_DELETED if we are
trying to read from a non-existent tablespace, or a
tablespace which is just now being dropped */
ibool sync, /*!< in: TRUE if synchronous aio is desired */
ulint mode, /*!< in: BUF_READ_IBUF_PAGES_ONLY, ...,
ORed to OS_AIO_SIMULATED_WAKE_LATER (see below
at read-ahead functions) */
ulint space, /*!< in: space id */
ulint zip_size,/*!< in: compressed page size, or 0 */
ibool unzip, /*!< in: TRUE=request uncompressed page */
ib_int64_t tablespace_version, /*!< in: if the space memory object has
this timestamp different from what we are giving here,
treat the tablespace as dropped; this is a timestamp we
use to stop dangling page reads from a tablespace
which we have DISCARDed + IMPORTed back */
ulint offset, /*!< in: page number */
trx_t* trx)
{
buf_page_t* bpage;
ulint wake_later;
*err = DB_SUCCESS;
wake_later = mode & OS_AIO_SIMULATED_WAKE_LATER;
mode = mode & ~OS_AIO_SIMULATED_WAKE_LATER;
if (trx_doublewrite
&& (space == TRX_SYS_SPACE
|| (srv_doublewrite_file && space == TRX_DOUBLEWRITE_SPACE))
&& ( (offset >= trx_doublewrite->block1
&& offset < trx_doublewrite->block1
+ TRX_SYS_DOUBLEWRITE_BLOCK_SIZE)
|| (offset >= trx_doublewrite->block2
&& offset < trx_doublewrite->block2
+ TRX_SYS_DOUBLEWRITE_BLOCK_SIZE))) {
ut_print_timestamp(stderr);
fprintf(stderr,
" InnoDB: Warning: trying to read"
" doublewrite buffer page %lu\n",
(ulong) offset);
return(0);
}
if (ibuf_bitmap_page(zip_size, offset)
|| trx_sys_hdr_page(space, offset)) {
/* Trx sys header is so low in the latching order that we play
safe and do not leave the i/o-completion to an asynchronous
i/o-thread. Ibuf bitmap pages must always be read with
syncronous i/o, to make sure they do not get involved in
thread deadlocks. */
sync = TRUE;
}
/* The following call will also check if the tablespace does not exist
or is being dropped; if we succeed in initing the page in the buffer
pool for read, then DISCARD cannot proceed until the read has
completed */
bpage = buf_page_init_for_read(err, mode, space, zip_size, unzip,
tablespace_version, offset);
if (bpage == NULL) {
/* bugfix: http://bugs.mysql.com/bug.php?id=43948 */
if (recv_recovery_is_on() && *err == DB_TABLESPACE_DELETED) {
/* hashed log recs must be treated here */
recv_addr_t* recv_addr;
mutex_enter(&(recv_sys->mutex));
if (recv_sys->apply_log_recs == FALSE) {
mutex_exit(&(recv_sys->mutex));
goto not_to_recover;
}
/* recv_get_fil_addr_struct() */
recv_addr = HASH_GET_FIRST(recv_sys->addr_hash,
hash_calc_hash(ut_fold_ulint_pair(space, offset),
recv_sys->addr_hash));
while (recv_addr) {
if ((recv_addr->space == space)
&& (recv_addr->page_no == offset)) {
break;
}
recv_addr = HASH_GET_NEXT(addr_hash, recv_addr);
}
if ((recv_addr == NULL)
|| (recv_addr->state == RECV_BEING_PROCESSED)
|| (recv_addr->state == RECV_PROCESSED)) {
mutex_exit(&(recv_sys->mutex));
goto not_to_recover;
}
fprintf(stderr, " (cannot find space: %lu)", space);
recv_addr->state = RECV_PROCESSED;
ut_a(recv_sys->n_addrs);
recv_sys->n_addrs--;
mutex_exit(&(recv_sys->mutex));
}
not_to_recover:
return(0);
}
#ifdef UNIV_DEBUG
if (buf_debug_prints) {
fprintf(stderr,
"Posting read request for page %lu, sync %lu\n",
(ulong) offset,
(ulong) sync);
}
#endif
ut_ad(buf_page_in_file(bpage));
if(sync) {
thd_wait_begin(NULL, THD_WAIT_DISKIO);
}
if (zip_size) {
*err = _fil_io(OS_FILE_READ | wake_later,
sync, space, zip_size, offset, 0, zip_size,
bpage->zip.data, bpage, trx);
} else {
ut_a(buf_page_get_state(bpage) == BUF_BLOCK_FILE_PAGE);
*err = _fil_io(OS_FILE_READ | wake_later,
sync, space, 0, offset, 0, UNIV_PAGE_SIZE,
((buf_block_t*) bpage)->frame, bpage, trx);
}
if (sync) {
thd_wait_end(NULL);
}
if (*err == DB_TABLESPACE_DELETED) {
buf_read_page_handle_error(bpage);
return(0);
}
if (srv_pass_corrupt_table) {
if (*err != DB_SUCCESS) {
bpage->is_corrupt = TRUE;
}
} else {
ut_a(*err == DB_SUCCESS);
}
if (sync) {
/* The i/o is already completed when we arrive from
fil_read */
if (!buf_page_io_complete(bpage)) {
return(0);
}
}
return(1);
}
/*************************************************************//**
Inserts an entry into a hash table. If an entry with the same fold number
is found, its node is updated to point to the new data, and no new node
is inserted. If btr_search_enabled is set to FALSE, we will only allow
updating existing nodes, but no new node is allowed to be added.
@return TRUE if succeed, FALSE if no more memory could be allocated */
UNIV_INTERN
ibool
ha_insert_for_fold_func(
/*====================*/
hash_table_t* table, /*!< in: hash table */
ulint fold, /*!< in: folded value of data; if a node with
the same fold value already exists, it is
updated to point to the same data, and no new
node is created! */
#if defined UNIV_AHI_DEBUG || defined UNIV_DEBUG
buf_block_t* block, /*!< in: buffer block containing the data */
#endif /* UNIV_AHI_DEBUG || UNIV_DEBUG */
const rec_t* data) /*!< in: data, must not be NULL */
{
hash_cell_t* cell;
ha_node_t* node;
ha_node_t* prev_node;
ulint hash;
ut_ad(data);
ut_ad(table);
ut_ad(table->magic_n == HASH_TABLE_MAGIC_N);
#if defined UNIV_AHI_DEBUG || defined UNIV_DEBUG
ut_a(block->frame == page_align(data));
#endif /* UNIV_AHI_DEBUG || UNIV_DEBUG */
#ifdef UNIV_SYNC_DEBUG
ut_ad(rw_lock_own(&btr_search_latch, RW_LOCK_EX));
#endif /* UNIV_SYNC_DEBUG */
ASSERT_HASH_MUTEX_OWN(table, fold);
ut_ad(btr_search_enabled);
hash = hash_calc_hash(fold, table);
cell = hash_get_nth_cell(table, hash);
prev_node = cell->node;
while (prev_node != NULL) {
if (prev_node->fold == fold) {
#if defined UNIV_AHI_DEBUG || defined UNIV_DEBUG
# ifndef UNIV_HOTBACKUP
if (table->adaptive) {
buf_block_t* prev_block = prev_node->block;
ut_a(prev_block->frame
== page_align(prev_node->data));
ut_a(prev_block->n_pointers > 0);
prev_block->n_pointers--;
block->n_pointers++;
}
# endif /* !UNIV_HOTBACKUP */
prev_node->block = block;
#endif /* UNIV_AHI_DEBUG || UNIV_DEBUG */
prev_node->data = data;
return(TRUE);
}
prev_node = prev_node->next;
}
/* We have to allocate a new chain node */
node = mem_heap_alloc(hash_get_heap(table, fold), sizeof(ha_node_t));
if (node == NULL) {
/* It was a btr search type memory heap and at the moment
no more memory could be allocated: return */
ut_ad(hash_get_heap(table, fold)->type & MEM_HEAP_BTR_SEARCH);
return(FALSE);
}
ha_node_set_data(node, block, data);
#if defined UNIV_AHI_DEBUG || defined UNIV_DEBUG
# ifndef UNIV_HOTBACKUP
if (table->adaptive) {
block->n_pointers++;
}
# endif /* !UNIV_HOTBACKUP */
#endif /* UNIV_AHI_DEBUG || UNIV_DEBUG */
node->fold = fold;
node->next = NULL;
prev_node = cell->node;
if (prev_node == NULL) {
cell->node = node;
return(TRUE);
}
while (prev_node->next != NULL) {
prev_node = prev_node->next;
}
prev_node->next = node;
return(TRUE);
}