mirror of
https://github.com/MariaDB/server.git
synced 2025-02-05 13:22:17 +01:00
bb47e575de
The invariant of write-ahead logging is that before any change to a
page is written to the data file, the corresponding log record must
must first have been durably written.
On crash recovery, there were some sloppy checks for this. Let us
implement accurate checks and flag an inconsistency as a hard error,
so that we can avoid further corruption of a corrupted database.
For data extraction from the corrupted database, innodb_force_recovery
can be used.
Before recovery is reading any data pages or invoking
buf_dblwr_t::recover() to recover torn pages from the
doublewrite buffer, InnoDB will have parsed the log until the
final LSN and updated log_sys.lsn to that. So, we can rely on
log_sys.lsn at all times. The doublewrite buffer recovery has been
refactored in such a way that the recv_sys.dblwr.pages may be consulted
while discovering files and their page sizes, but nothing will be
written back to data files before buf_dblwr_t::recover() is invoked.
A section of the test mariabackup.innodb_redo_overwrite
that is parsing some mariadb-backup --backup output has
been removed, because that output "redo log block is overwritten"
would often be missing in a Microsoft Windows environment
as a result of these changes.
recv_max_page_lsn, recv_lsn_checks_on: Remove.
recv_sys_t::validate_checkpoint(): Validate the write-ahead-logging
condition at the end of the recovery.
recv_dblwr_t::validate_page(): Keep track of the maximum LSN
(if we are checking a non-doublewrite copy of a page) but
do not complain LSN being in the future. The doublewrite buffer
is a special case, because it will be read early during recovery.
Besides, starting with commit 762bcb81b5
the dblwr=true copies of pages may legitimately be "too new".
recv_dblwr_t::find_page(): Find a valid page with the smallest
FIL_PAGE_LSN that is in the valid range for recovery.
recv_dblwr_t::restore_first_page(): Replaced by find_page().
Only buf_dblwr_t::recover() will write to data files.
buf_dblwr_t::recover(): Simplify the message output. Do attempt
doublewrite recovery on user page read error. Ignore doublewrite
pages whose FIL_PAGE_LSN is outside the usable bounds. Previously,
we could wrongly recover a too new page from the doublewrite buffer.
It is unlikely that this could have lead to an actual error.
Write back all recovered pages from the doublewrite buffer here,
including for the first page of any tablespace.
buf_page_is_corrupted(): Distinguish the return values
CORRUPTED_FUTURE_LSN and CORRUPTED_OTHER.
buf_page_check_corrupt(): Return the error code DB_CORRUPTION
in case the LSN is in the future.
Datafile::read_first_page(): Handle FSP_SPACE_FLAGS=0xffffffff
in the same way on both 32-bit and 64-bit architectures.
Datafile::read_first_page_flags(): Split from read_first_page().
Take a copy of the first page as a parameter.
recv_sys_t::free_corrupted_page(): Take the file as a parameter
and return whether a message was displayed. This avoids some duplicated
and incomplete error messages.
buf_page_t::read_complete(): Remove some redundant output and always
display the name of the corrupted file. Never return DB_FAIL;
use it only in internal error handling.
IORequest::read_complete(): Assume that buf_page_t::read_complete()
will have reported any error.
fil_space_t::set_corrupted(): Return whether this is the first time
the tablespace had been flagged as corrupted.
Datafile::validate_first_page(), fil_node_open_file_low(),
fil_node_open_file(), fil_space_t::read_page0(),
fil_node_t::read_page0(): Add a parameter for a copy of the
first page, and a parameter to indicate whether the FIL_PAGE_LSN
check should be suppressed. Before buf_dblwr_t::recover() is
invoked, we cannot validate the FIL_PAGE_LSN, but we can trust the
FSP_SPACE_FLAGS and the tablespace ID that may be present in a
potentially too new copy of a page.
Reviewed by: Debarun Banerjee
45 lines
2.9 KiB
Text
45 lines
2.9 KiB
Text
call mtr.add_suppression("Plugin 'file_key_management'");
|
|
call mtr.add_suppression("Plugin 'InnoDB' init function returned error.");
|
|
call mtr.add_suppression("InnoDB: The page \\[page id: space=[1-9][0-9]*, page number=[1-9][0-9]*\\] in file '.*test.t[1-4]\\.ibd' cannot be decrypted; key_version=1");
|
|
call mtr.add_suppression("InnoDB: File '.*test/t[1234]\\.ibd' is corrupted");
|
|
call mtr.add_suppression("InnoDB: Recovery failed to read page");
|
|
call mtr.add_suppression("InnoDB: Unable to decompress .*.test.t[12]\\.ibd\\[page id: space=[1-9][0-9]*, page number=[0-9]+\\]");
|
|
call mtr.add_suppression("InnoDB: Database page corruption on disk or a failed read of file '.*test.t[12]\\.ibd'");
|
|
call mtr.add_suppression("InnoDB: Failed to read page .* from file '.*'");
|
|
call mtr.add_suppression("InnoDB: OPT_PAGE_CHECKSUM mismatch");
|
|
call mtr.add_suppression("InnoDB: Set innodb_force_recovery=1 to ignore corruption");
|
|
call mtr.add_suppression("InnoDB: (Unable to apply log to|Discarding log for) corrupted page ");
|
|
call mtr.add_suppression("InnoDB: Plugin initialization aborted");
|
|
call mtr.add_suppression("Plugin 'InnoDB' registration as a STORAGE ENGINE failed");
|
|
call mtr.add_suppression("\\[ERROR\\] InnoDB: Cannot decrypt \\[page id: space=");
|
|
# restart: --file-key-management-filename=MYSQL_TEST_DIR/std_data/keys2.txt
|
|
# Wait max 10 min for key encryption threads to encrypt all spaces
|
|
SET GLOBAL innodb_file_per_table = ON;
|
|
create table t1(a int not null primary key auto_increment, c char(250), b blob, index(b(10))) engine=innodb row_format=compressed encrypted=yes encryption_key_id=4;
|
|
create table t2(a int not null primary key auto_increment, c char(250), b blob, index(b(10))) engine=innodb row_format=compressed;
|
|
create table t3(a int not null primary key auto_increment, c char(250), b blob, index(b(10))) engine=innodb encrypted=yes encryption_key_id=4;
|
|
create table t4(a int not null primary key auto_increment, c char(250), b blob, index(b(10))) engine=innodb;
|
|
begin;
|
|
insert into t2 select * from t1;
|
|
insert into t3 select * from t1;
|
|
insert into t4 select * from t1;
|
|
commit;
|
|
set global innodb_log_checkpoint_now=on;
|
|
SET GLOBAL innodb_flush_log_at_trx_commit=1;
|
|
begin;
|
|
update t1 set c = repeat('secret3', 20);
|
|
update t2 set c = repeat('secret4', 20);
|
|
update t3 set c = repeat('secret4', 20);
|
|
update t4 set c = repeat('secret4', 20);
|
|
insert into t1 (c,b) values (repeat('secret5',20), repeat('secret6',6000));
|
|
insert into t2 (c,b) values (repeat('secret7',20), repeat('secret8',6000));
|
|
insert into t3 (c,b) values (repeat('secret9',20), repeat('secre10',6000));
|
|
insert into t4 (c,b) values (repeat('secre11',20), repeat('secre12',6000));
|
|
COMMIT;
|
|
# Kill the server
|
|
# restart: --file-key-management-filename=MYSQL_TEST_DIR/std_data/keys2.txt
|
|
# Kill the server
|
|
# restart: --innodb-force-recovery=1
|
|
# Kill the server
|
|
# restart: --file-key-management-filename=MYSQL_TEST_DIR/std_data/keys2.txt
|
|
drop table t1, t2,t3,t4;
|