mirror of
https://github.com/MariaDB/server.git
synced 2025-01-30 18:41:56 +01:00
685d958e38
The InnoDB redo log used to be formatted in blocks of 512 bytes. The log blocks were encrypted and the checksum was calculated while holding log_sys.mutex, creating a serious scalability bottleneck. We remove the fixed-size redo log block structure altogether and essentially turn every mini-transaction into a log block of its own. This allows encryption and checksum calculations to be performed on local mtr_t::m_log buffers, before acquiring log_sys.mutex. The mutex only protects a memcpy() of the data to the shared log_sys.buf, as well as the padding of the log, in case the to-be-written part of the log would not end in a block boundary of the underlying storage. For now, the "padding" consists of writing a single NUL byte, to allow recovery and mariadb-backup to detect the end of the circular log faster. Like the previous implementation, we will overwrite the last log block over and over again, until it has been completely filled. It would be possible to write only up to the last completed block (if no more recent write was requested), or to write dummy FILE_CHECKPOINT records to fill the incomplete block, by invoking the currently disabled function log_pad(). This would require adjustments to some logic around log checkpoints, page flushing, and shutdown. An upgrade after a crash of any previous version is not supported. Logically empty log files from a previous version will be upgraded. An attempt to start up InnoDB without a valid ib_logfile0 will be refused. Previously, the redo log used to be created automatically if it was missing. Only with with innodb_force_recovery=6, it is possible to start InnoDB in read-only mode even if the log file does not exist. This allows the contents of a possibly corrupted database to be dumped. Because a prepared backup from an earlier version of mariadb-backup will create a 0-sized log file, we will allow an upgrade from such log files, provided that the FIL_PAGE_FILE_FLUSH_LSN in the system tablespace looks valid. The 512-byte log checkpoint blocks at 0x200 and 0x600 will be replaced with 64-byte log checkpoint blocks at 0x1000 and 0x2000. The start of log records will move from 0x800 to 0x3000. This allows us to use 4096-byte aligned blocks for all I/O in a future revision. We extend the MDEV-12353 redo log record format as follows. (1) Empty mini-transactions or extra NUL bytes will not be allowed. (2) The end-of-minitransaction marker (a NUL byte) will be replaced with a 1-bit sequence number, which will be toggled each time when the circular log file wraps back to the beginning. (3) After the sequence bit, a CRC-32C checksum of all data (excluding the sequence bit) will written. (4) If the log is encrypted, 8 bytes will be written before the checksum and included in it. This is part of the initialization vector (IV) of encrypted log data. (5) File names, page numbers, and checkpoint information will not be encrypted. Only the payload bytes of page-level log will be encrypted. The tablespace ID and page number will form part of the IV. (6) For padding, arbitrary-length FILE_CHECKPOINT records may be written, with all-zero payload, and with the normal end marker and checksum. The minimum size is 7 bytes, or 7+8 with innodb_encrypt_log=ON. In mariadb-backup and in Galera snapshot transfer (SST) scripts, we will no longer remove ib_logfile0 or create an empty ib_logfile0. Server startup will require a valid log file. When resizing the log, we will create a logically empty ib_logfile101 at the current LSN and use an atomic rename to replace ib_logfile0 with it. See the test innodb.log_file_size. Because there is no mandatory padding in the log file, we are able to create a dummy log file as of an arbitrary log sequence number. See the test mariabackup.huge_lsn. The parameter innodb_log_write_ahead_size and the INFORMATION_SCHEMA.INNODB_METRICS counter log_padded will be removed. The minimum value of innodb_log_buffer_size will be increased to 2MiB (because log_sys.buf will replace recv_sys.buf) and the increment adjusted to 4096 bytes (the maximum log block size). The following INFORMATION_SCHEMA.INNODB_METRICS counters will be removed: os_log_fsyncs os_log_pending_fsyncs log_pending_log_flushes log_pending_checkpoint_writes The following status variables will be removed: Innodb_os_log_fsyncs (this is included in Innodb_data_fsyncs) Innodb_os_log_pending_fsyncs (this was limited to at most 1 by design) log_sys.get_block_size(): Return the physical block size of the log file. This is only implemented on Linux and Microsoft Windows for now, and for the power-of-2 block sizes between 64 and 4096 bytes (the minimum and maximum size of a checkpoint block). If the block size is anything else, the traditional 512-byte size will be used via normal file system buffering. If the file system buffers can be bypassed, a message like the following will be issued: InnoDB: File system buffers for log disabled (block size=512 bytes) InnoDB: File system buffers for log disabled (block size=4096 bytes) This has been tested on Linux and Microsoft Windows with both sizes. On Linux, only enable O_DIRECT on the log for innodb_flush_method=O_DSYNC. Tests in 3 different environments where the log is stored in a device with a physical block size of 512 bytes are yielding better throughput without O_DIRECT. This could be due to the fact that in the event the last log block is being overwritten (if multiple transactions would become durable at the same time, and each of will write a small number of bytes to the last log block), it should be faster to re-copy data from log_sys.buf or log_sys.flush_buf to the kernel buffer, to be finally written at fdatasync() time. The parameter innodb_flush_method=O_DSYNC will imply O_DIRECT for data files. This option will enable O_DIRECT on the log file on Linux. It may be unsafe to use when the storage device does not support FUA (Force Unit Access) mode. When the server is compiled WITH_PMEM=ON, we will use memory-mapped I/O for the log file if the log resides on a "mount -o dax" device. We will identify PMEM in a start-up message: InnoDB: log sequence number 0 (memory-mapped); transaction id 3 On Linux, we will also invoke mmap() on any ib_logfile0 that resides in /dev/shm, effectively treating the log file as persistent memory. This should speed up "./mtr --mem" and increase the test coverage of PMEM on non-PMEM hardware. It also allows users to estimate how much the performance would be improved by installing persistent memory. On other tmpfs file systems such as /run, we will not use mmap(). mariadb-backup: Eliminated several variables. We will refer directly to recv_sys and log_sys. backup_wait_for_lsn(): Detect non-progress of xtrabackup_copy_logfile(). In this new log format with arbitrary-sized blocks, we can only detect log file overrun indirectly, by observing that the scanned log sequence number is not advancing. xtrabackup_copy_logfile(): On PMEM, do not modify the sequence bit, because we are not allowed to modify the server's log file, and our memory mapping is read-only. trx_flush_log_if_needed_low(): Do not use the callback on pmem. Using neither flush_lock nor write_lock around PMEM writes seems to yield the best performance. The pmem_persist() calls may still be somewhat slower than the pwrite() and fdatasync() based interface (PMEM mounted without -o dax). recv_sys_t::buf: Remove. We will use log_sys.buf for parsing. recv_sys_t::MTR_SIZE_MAX: Replaces RECV_SCAN_SIZE. recv_sys_t::file_checkpoint: Renamed from mlog_checkpoint_lsn. recv_sys_t, log_sys_t: Removed many data members. recv_sys.lsn: Renamed from recv_sys.recovered_lsn. recv_sys.offset: Renamed from recv_sys.recovered_offset. log_sys.buf_size: Replaces srv_log_buffer_size. recv_buf: A smart pointer that wraps log_sys.buf[recv_sys.offset] when the buffer is being allocated from the memory heap. recv_ring: A smart pointer that wraps a circular log_sys.buf[] that is backed by ib_logfile0. The pointer will wrap from recv_sys.len (log_sys.file_size) to log_sys.START_OFFSET. For the record that wraps around, we may copy file name or record payload data to the auxiliary buffer decrypt_buf in order to have a contiguous block of memory. The maximum size of a record is less than innodb_page_size bytes. recv_sys_t::parse(): Take the smart pointer as a template parameter. Do not temporarily add a trailing NUL byte to FILE_ records, because we are not supposed to modify the memory-mapped log file. (It is attached in read-write mode already during recovery.) recv_sys_t::parse_mtr(): Wrapper for recv_sys_t::parse(). recv_sys_t::parse_pmem(): Like parse_mtr(), but if PREMATURE_EOF would be returned on PMEM, use recv_ring to wrap around the buffer to the start. mtr_t::finish_write(), log_close(): Do not enforce log_sys.max_buf_free on PMEM, because it has no meaning on the mmap-based log. log_sys.write_to_buf: Count writes to log_sys.buf. Replaces srv_stats.log_write_requests and export_vars.innodb_log_write_requests. Protected by log_sys.mutex. Updated consistently in log_close(). Previously, mtr_t::commit() conditionally updated the count, which was inconsistent. log_sys.write_to_log: Count swaps of log_sys.buf and log_sys.flush_buf, for writing to log_sys.log (the ib_logfile0). Replaces srv_stats.log_writes and export_vars.innodb_log_writes. Protected by log_sys.mutex. log_sys.waits: Count waits in append_prepare(). Replaces srv_stats.log_waits and export_vars.innodb_log_waits. recv_recover_page(): Do not unnecessarily acquire log_sys.flush_order_mutex. We are inserting the blocks in arbitary order anyway, to be adjusted in recv_sys.apply(true). We will change the definition of flush_lock and write_lock to avoid potential false sharing. Depending on sizeof(log_sys) and CPU_LEVEL1_DCACHE_LINESIZE, the flush_lock and write_lock could share a cache line with each other or with the last data members of log_sys. Thanks to Matthias Leich for providing https://rr-project.org traces for various failures during the development, and to Thirunarayanan Balathandayuthapani for his help in debugging some of the recovery code. And thanks to the developers of the rr debugger for a tool without which extensive changes to InnoDB would be very challenging to get right. Thanks to Vladislav Vaintroub for useful feedback and to him, Axel Schwenke and Krunal Bauskar for testing the performance.
278 lines
7.8 KiB
C++
278 lines
7.8 KiB
C++
/*****************************************************************************
|
|
|
|
Copyright (c) 2013, 2016, Oracle and/or its affiliates. All Rights Reserved.
|
|
Copyright (c) 2016, 2022, MariaDB Corporation.
|
|
|
|
This program is free software; you can redistribute it and/or modify it under
|
|
the terms of the GNU General Public License as published by the Free Software
|
|
Foundation; version 2 of the License.
|
|
|
|
This program is distributed in the hope that it will be useful, but WITHOUT
|
|
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
|
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License along with
|
|
this program; if not, write to the Free Software Foundation, Inc.,
|
|
51 Franklin Street, Fifth Floor, Boston, MA 02110-1335 USA
|
|
|
|
*****************************************************************************/
|
|
|
|
/**************************************************//**
|
|
@file include/fsp0sysspace.h
|
|
Multi file, shared, system tablespace implementation.
|
|
|
|
Created 2013-7-26 by Kevin Lewis
|
|
*******************************************************/
|
|
|
|
#ifndef fsp0sysspace_h
|
|
#define fsp0sysspace_h
|
|
|
|
#include "fsp0space.h"
|
|
|
|
/** If the last data file is auto-extended, we add this many pages to it
|
|
at a time. We have to make this public because it is a config variable. */
|
|
extern uint sys_tablespace_auto_extend_increment;
|
|
|
|
/** Data structure that contains the information about shared tablespaces.
|
|
Currently this can be the system tablespace or a temporary table tablespace */
|
|
class SysTablespace : public Tablespace
|
|
{
|
|
public:
|
|
|
|
SysTablespace()
|
|
:
|
|
m_auto_extend_last_file(),
|
|
m_last_file_size_max(),
|
|
m_created_new_raw(),
|
|
m_is_tablespace_full(false),
|
|
m_sanity_checks_done(false)
|
|
{
|
|
/* No op */
|
|
}
|
|
|
|
~SysTablespace() override
|
|
{
|
|
shutdown();
|
|
}
|
|
|
|
/** Set tablespace full status
|
|
@param[in] is_full true if full */
|
|
void set_tablespace_full_status(bool is_full)
|
|
{
|
|
m_is_tablespace_full = is_full;
|
|
}
|
|
|
|
/** Get tablespace full status
|
|
@return true if table is full */
|
|
bool get_tablespace_full_status()
|
|
{
|
|
return(m_is_tablespace_full);
|
|
}
|
|
|
|
/** Set sanity check status
|
|
@param[in] status true if sanity checks are done */
|
|
void set_sanity_check_status(bool status)
|
|
{
|
|
m_sanity_checks_done = status;
|
|
}
|
|
|
|
/** Get sanity check status
|
|
@return true if sanity checks are done */
|
|
bool get_sanity_check_status()
|
|
{
|
|
return(m_sanity_checks_done);
|
|
}
|
|
|
|
/** Parse the input params and populate member variables.
|
|
@param filepath path to data files
|
|
@param supports_raw true if it supports raw devices
|
|
@return true on success parse */
|
|
bool parse_params(const char* filepath, bool supports_raw);
|
|
|
|
/** Check the data file specification.
|
|
@param[out] create_new_db true if a new database
|
|
is to be created
|
|
@param[in] min_expected_size expected tablespace
|
|
size in bytes
|
|
@return DB_SUCCESS if all OK else error code */
|
|
dberr_t check_file_spec(
|
|
bool* create_new_db,
|
|
ulint min_expected_tablespace_size);
|
|
|
|
/** Free the memory allocated by parse() */
|
|
void shutdown();
|
|
|
|
/** Normalize the file size, convert to extents. */
|
|
void normalize_size();
|
|
|
|
/**
|
|
@return true if a new raw device was created. */
|
|
bool created_new_raw() const
|
|
{
|
|
return(m_created_new_raw);
|
|
}
|
|
|
|
/**
|
|
@return auto_extend value setting */
|
|
ulint can_auto_extend_last_file() const
|
|
{
|
|
return(m_auto_extend_last_file);
|
|
}
|
|
|
|
/** Set the last file size.
|
|
@param[in] size the size to set */
|
|
void set_last_file_size(uint32_t size)
|
|
{
|
|
ut_ad(!m_files.empty());
|
|
m_files.back().m_size = size;
|
|
}
|
|
|
|
/** Get the size of the last data file in the tablespace
|
|
@return the size of the last data file in the array */
|
|
uint32_t last_file_size() const
|
|
{
|
|
ut_ad(!m_files.empty());
|
|
return(m_files.back().m_size);
|
|
}
|
|
|
|
/**
|
|
@return the autoextend increment in pages. */
|
|
uint32_t get_autoextend_increment() const
|
|
{
|
|
return sys_tablespace_auto_extend_increment
|
|
<< (20 - srv_page_size_shift);
|
|
}
|
|
|
|
/**
|
|
@return next increment size */
|
|
uint32_t get_increment() const;
|
|
|
|
/** Open or create the data files
|
|
@param[in] is_temp whether this is a temporary tablespace
|
|
@param[in] create_new_db whether we are creating a new database
|
|
@param[out] sum_new_sizes sum of sizes of the new files added
|
|
@return DB_SUCCESS or error code */
|
|
dberr_t open_or_create(
|
|
bool is_temp,
|
|
bool create_new_db,
|
|
ulint* sum_new_sizes)
|
|
MY_ATTRIBUTE((warn_unused_result));
|
|
|
|
private:
|
|
/** Check the tablespace header for this tablespace.
|
|
@return DB_SUCCESS or error code */
|
|
inline dberr_t read_lsn_and_check_flags();
|
|
|
|
/**
|
|
@return true if the last file size is valid. */
|
|
bool is_valid_size() const
|
|
{
|
|
return(m_last_file_size_max >= last_file_size());
|
|
}
|
|
|
|
/**
|
|
@return true if configured to use raw devices */
|
|
bool has_raw_device();
|
|
|
|
/** Note that the data file was not found.
|
|
@param[in] file data file object
|
|
@param[out] create_new_db true if a new instance to be created
|
|
@return DB_SUCESS or error code */
|
|
dberr_t file_not_found(Datafile& file, bool* create_new_db);
|
|
|
|
/** Note that the data file was found.
|
|
@param[in,out] file data file object
|
|
@return true if a new instance to be created */
|
|
bool file_found(Datafile& file);
|
|
|
|
/** Create a data file.
|
|
@param[in,out] file data file object
|
|
@return DB_SUCCESS or error code */
|
|
dberr_t create(Datafile& file);
|
|
|
|
/** Create a data file.
|
|
@param[in,out] file data file object
|
|
@return DB_SUCCESS or error code */
|
|
dberr_t create_file(Datafile& file);
|
|
|
|
/** Open a data file.
|
|
@param[in,out] file data file object
|
|
@return DB_SUCCESS or error code */
|
|
dberr_t open_file(Datafile& file);
|
|
|
|
/** Set the size of the file.
|
|
@param[in,out] file data file object
|
|
@return DB_SUCCESS or error code */
|
|
dberr_t set_size(Datafile& file);
|
|
|
|
/** Convert a numeric string that optionally ends in G or M, to a
|
|
number containing megabytes.
|
|
@param[in] ptr string with a quantity in bytes
|
|
@param[out] megs the number in megabytes
|
|
@return next character in string */
|
|
static char* parse_units(char* ptr, ulint* megs);
|
|
|
|
private:
|
|
enum file_status_t {
|
|
FILE_STATUS_VOID = 0, /** status not set */
|
|
FILE_STATUS_RW_PERMISSION_ERROR,/** permission error */
|
|
FILE_STATUS_READ_WRITE_ERROR, /** not readable/writable */
|
|
FILE_STATUS_NOT_REGULAR_FILE_ERROR /** not a regular file */
|
|
};
|
|
|
|
/** Verify the size of the physical file
|
|
@param[in] file data file object
|
|
@return DB_SUCCESS if OK else error code. */
|
|
dberr_t check_size(Datafile& file);
|
|
|
|
/** Check if a file can be opened in the correct mode.
|
|
@param[in,out] file data file object
|
|
@param[out] reason exact reason if file_status check failed.
|
|
@return DB_SUCCESS or error code. */
|
|
dberr_t check_file_status(
|
|
const Datafile& file,
|
|
file_status_t& reason);
|
|
|
|
/* DATA MEMBERS */
|
|
|
|
/** if true, then we auto-extend the last data file */
|
|
bool m_auto_extend_last_file;
|
|
|
|
/** maximum size of the last data file (0=unlimited) */
|
|
ulint m_last_file_size_max;
|
|
|
|
/** If the following is true we do not allow
|
|
inserts etc. This protects the user from forgetting
|
|
the 'newraw' keyword to my.cnf */
|
|
bool m_created_new_raw;
|
|
|
|
/** Tablespace full status */
|
|
bool m_is_tablespace_full;
|
|
|
|
/** if false, then sanity checks are still pending */
|
|
bool m_sanity_checks_done;
|
|
};
|
|
|
|
/* GLOBAL OBJECTS */
|
|
|
|
/** The control info of the system tablespace. */
|
|
extern SysTablespace srv_sys_space;
|
|
|
|
/** The control info of a temporary table shared tablespace. */
|
|
extern SysTablespace srv_tmp_space;
|
|
|
|
/** Check if the space_id is for a system-tablespace (shared + temp).
|
|
@param[in] id Space ID to check
|
|
@return true if id is a system tablespace, false if not. */
|
|
inline bool is_system_tablespace(uint32_t id)
|
|
{
|
|
return id == TRX_SYS_SPACE || id == SRV_TMP_SPACE_ID;
|
|
}
|
|
|
|
/** Check if predefined shared tablespace.
|
|
@return true if predefined shared tablespace */
|
|
inline bool is_predefined_tablespace(uint32_t id)
|
|
{
|
|
return is_system_tablespace(id) || srv_is_undo_tablespace(id);
|
|
}
|
|
#endif /* fsp0sysspace_h */
|