mirror/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2026-05-07 07:35:32 +02:00
Code Issues Projects Releases Packages Wiki Activity

MDEV-23855: Remove fil_system.LRU and reduce fil_system.mutex contention

Browse source 
Also fixes MDEV-23929: innodb_flush_neighbors is not being ignored
for system tablespace on SSD

When the maximum configured number of file is exceeded, InnoDB will
close data files. We used to maintain a fil_system.LRU list and
a counter fil_node_t::n_pending to achieve this, at the huge cost
of multiple fil_system.mutex operations per I/O operation.

fil_node_open_file_low(): Implement a FIFO replacement policy:
The last opened file will be moved to the end of fil_system.space_list,
and files will be closed from the start of the list. However, we will
not move tablespaces in fil_system.space_list while
i_s_tablespaces_encryption_fill_table() is executing
(producing output for INFORMATION_SCHEMA.INNODB_TABLESPACES_ENCRYPTION)
because it may cause information of some tablespaces to go missing.
We also avoid this in mariabackup --backup because datafiles_iter_next()
assumes that the ordering is not changed.

IORequest: Fold more parameters to IORequest::type.

fil_space_t::io(): Replaces fil_io().

fil_space_t::flush(): Replaces fil_flush().

OS_AIO_IBUF: Remove. We will always issue synchronous reads of the
change buffer pages in buf_read_page_low().

We will always ignore some errors for background reads.

This should reduce fil_system.mutex contention a little.

fil_node_t::complete_write(): Replaces fil_node_t::complete_io().
On both read and write completion, fil_space_t::release_for_io()
will have to be called.

fil_space_t::io(): Do not acquire fil_system.mutex in the normal
code path.

xb_delta_open_matching_space(): Do not try to open the system tablespace
which was already opened. This fixes a file sharing violation in
mariabackup --prepare --incremental.

Reviewed by: Vladislav Vaintroub
This commit is contained in:
Marko Mäkelä 2020-10-26 15:59:30 +02:00
commit 45ed9dd957
39 changed files with 1303 additions and 1900 deletions
Download patch file Download diff file Expand all files Collapse all files

10
storage/innobase/include/os0file.ic
View file

@ -206,7 +206,6 @@ function!
Performance schema wrapper function of os_aio() which requests
an asynchronous i/o operation.
@param[in,type] type IO request context
@param[in] mode IO mode
@param[in] name Name of the file or path as NUL terminated
string
@param[in] file Open file handle
@ -226,8 +225,7 @@ an asynchronous i/o operation.
UNIV_INLINE
dberr_t
pfs_os_aio_func(
IORequest& type,
ulint mode,
const IORequest&type,
const char* name,
pfs_os_file_t file,
void* buf,
@ -242,8 +240,6 @@ pfs_os_aio_func(
PSI_file_locker_state state;
struct PSI_file_locker* locker = NULL;
ut_ad(type.validate());
/* Register the read or write I/O depending on "type" */
register_pfs_file_io_begin(
&state, locker, file, n,
@ -251,7 +247,7 @@ pfs_os_aio_func(
src_file, src_line);
dberr_t result = os_aio_func(
type, mode, name, file, buf, offset, n, read_only, m1, m2);
type, name, file, buf, offset, n, read_only, m1, m2);
register_pfs_file_io_end(locker, n);
@ -284,8 +280,6 @@ pfs_os_file_read_func(
PSI_file_locker_state state;
struct PSI_file_locker* locker = NULL;
ut_ad(type.validate());
register_pfs_file_io_begin(
&state, locker, file, n, PSI_FILE_READ, src_file, src_line);