事务提交与XLog日志分析

根据预写式日志WAL的定义，数据库在修改磁盘上的元组前，必须先将日志记录刷回到磁盘。XLog的组织形式如下，依次为日志记录头，日志类型（事务操作日志、事务提交或终止日志或是检查点日志等）、备份文件块描述信息以及备份文件块数据。数据库系统把各种需要记录日志的数据分类，分配给与他们对应的资源管理器号，系统在恢复或者读取日志记录时，能够通过资源管理器号和日志头信息中的xl_info字段（高4位），知道数据库对源数据做了哪种操作，从而正确的调用相应的响应函数（如redo函数等）。

PG_RMGR(RM_XLOG_ID, "XLOG", xlog_redo, xlog_desc, NULL, NULL)
PG_RMGR(RM_XACT_ID, "Transaction", xact_redo, xact_desc, NULL, NULL)
PG_RMGR(RM_SMGR_ID, "Storage", smgr_redo, smgr_desc, NULL, NULL)
PG_RMGR(RM_CLOG_ID, "CLOG", clog_redo, clog_desc, NULL, NULL)
PG_RMGR(RM_DBASE_ID, "Database", dbase_redo, dbase_desc, NULL, NULL)
PG_RMGR(RM_TBLSPC_ID, "Tablespace", tblspc_redo, tblspc_desc, NULL, NULL)
PG_RMGR(RM_MULTIXACT_ID, "MultiXact", multixact_redo, multixact_desc, NULL, NULL)
PG_RMGR(RM_RELMAP_ID, "RelMap", relmap_redo, relmap_desc, NULL, NULL)
PG_RMGR(RM_STANDBY_ID, "Standby", standby_redo, standby_desc, NULL, NULL)
PG_RMGR(RM_HEAP2_ID, "Heap2", heap2_redo, heap2_desc, NULL, NULL)
PG_RMGR(RM_HEAP_ID, "Heap", heap_redo, heap_desc, NULL, NULL)
PG_RMGR(RM_BTREE_ID, "Btree", btree_redo, btree_desc, NULL, NULL)
PG_RMGR(RM_HASH_ID, "Hash", hash_redo, hash_desc, NULL, NULL)
PG_RMGR(RM_GIN_ID, "Gin", gin_redo, gin_desc, gin_xlog_startup, gin_xlog_cleanup)
PG_RMGR(RM_GIST_ID, "Gist", gist_redo, gist_desc, gist_xlog_startup, gist_xlog_cleanup)
PG_RMGR(RM_SEQ_ID, "Sequence", seq_redo, seq_desc, NULL, NULL)
PG_RMGR(RM_SPGIST_ID, "SPGist", spg_redo, spg_desc, spg_xlog_startup, spg_xlog_cleanup)

日志头信息的描述结构体为XLogRecord，其定义如下所示，xl_len记录了RMGR数据的长度，xid记录了修改事务ID，xl_tot_len记录了整条日志记录的长度。单条XLOG日志记录支持最多备份4个文件块，如果内存中的文件块需要进行备份，每次就把xl_info低4位中的某一位依次置1，并将内存块附在XLOG日志记录中。

typedef struct XLogRecord
{
	uint32		xl_tot_len;		/* total len of entire record */
	TransactionId xl_xid;		/* xact id */
	uint32		xl_len;			/* total len of rmgr data */
	uint8		xl_info;		/* flag bits, see below */
	RmgrId		xl_rmid;		/* resource manager for this record */
	/* 2 bytes of padding here, initialize to zero */
	XLogRecPtr	xl_prev;		/* ptr to previous record in log */
	pg_crc32	xl_crc;			/* CRC for this record */

	/* If MAXALIGN==8, there are 4 wasted bytes here */

	/* ACTUAL LOG DATA FOLLOWS AT END OF STRUCT */

} XLogRecord;

typedef struct RmgrData
{
	const char *rm_name;
	void		(*rm_redo) (XLogRecPtr lsn, struct XLogRecord *rptr);
	void		(*rm_desc) (StringInfo buf, uint8 xl_info, char *rec);
	void		(*rm_startup) (void);
	void		(*rm_cleanup) (void);
} RmgrData;

typedef struct BkpBlock
{
	RelFileNode node;			/* relation containing block */
	ForkNumber	fork;			/* fork within the relation */
	BlockNumber block;			/* block number */
	uint16		hole_offset;	/* number of bytes before "hole" */
	uint16		hole_length;	/* number of bytes in "hole" */

	/* ACTUAL BLOCK DATA FOLLOWS AT END OF STRUCT */
} BkpBlock;

XLOG日志记录在内存中以链表的形式组织，其描述结构如下，

typedef struct XLogRecData
{
	char	   *data;			/* start of rmgr data to include */
	uint32		len;			/* length of rmgr data to include */
	Buffer		buffer;			/* buffer associated with data, if any */
	bool		buffer_std;		/* buffer has standard pd_lower/pd_upper */
	struct XLogRecData *next;	/* next struct in chain, or NULL */
} XLogRecData;