Revamp the WAL record format.

Each WAL record now carries information about the modified relation and
block(s) in a standardized format. That makes it easier to write tools that
need that information, like pg_rewind, prefetching the blocks to speed up
recovery, etc.

There's a whole new API for building WAL records, replacing the XLogRecData
chains used previously. The new API consists of XLogRegister* functions,
which are called for each buffer and chunk of data that is added to the
record. The new API also gives more control over when a full-page image is
written, by passing flags to the XLogRegisterBuffer function.

This also simplifies the XLogReadBufferForRedo() calls. The function can dig
the relation and block number from the WAL record, so they no longer need to
be passed as arguments.

For the convenience of redo routines, XLogReader now disects each WAL record
after reading it, copying the main data part and the per-block data into
MAXALIGNed buffers. The data chunks are not aligned within the WAL record,
but the redo routines can assume that the pointers returned by XLogRecGet*
functions are. Redo routines are now passed the XLogReaderState, which
contains the record in the already-disected format, instead of the plain
XLogRecord.

The new record format also makes the fixed size XLogRecord header smaller,
by removing the xl_len field. The length of the "main data" portion is now
stored at the end of the WAL record, and there's a separate header after
XLogRecord for it. The alignment padding at the end of XLogRecord is also
removed. This compansates for the fact that the new format would otherwise
be more bulky than the old format.

Reviewed by Andres Freund, Amit Kapila, Michael Paquier, Alvaro Herrera,
Fujii Masao.

1 files changed, 76 insertions, 1 deletions

diff --git a/src/include/access/xlogreader.h b/src/include/access/xlogreader.h
index ea873a2d9c7..eb6cc8996a5 100644
--- a/src/include/access/xlogreader.h
+++ b/src/include/access/xlogreader.h
@@ -14,12 +14,18 @@
  *
  *		The basic idea is to allocate an XLogReaderState via
  *		XLogReaderAllocate(), and call XLogReadRecord() until it returns NULL.
+ *
+ *		After reading a record with XLogReadRecord(), it's decomposed into
+ *		the per-block and main data parts, and the parts can be accessed
+ *		with the XLogRec* macros and functions. You can also decode a
+ *		record that's already constructed in memory, without reading from
+ *		disk, by calling the DecodeXLogRecord() function.
  *-------------------------------------------------------------------------
  */
 #ifndef XLOGREADER_H
 #define XLOGREADER_H
 
-#include "access/xlog_internal.h"
+#include "access/xlogrecord.h"
 
 typedef struct XLogReaderState XLogReaderState;
 
@@ -31,6 +37,32 @@ typedef int (*XLogPageReadCB) (XLogReaderState *xlogreader,
 										   char *readBuf,
 										   TimeLineID *pageTLI);
 
+typedef struct
+{
+	/* Is this block ref in use? */
+	bool		in_use;
+
+	/* Identify the block this refers to */
+	RelFileNode rnode;
+	ForkNumber	forknum;
+	BlockNumber blkno;
+
+	/* copy of the fork_flags field from the XLogRecordBlockHeader */
+	uint8		flags;
+
+	/* Information on full-page image, if any */
+	bool		has_image;
+	char	   *bkp_image;
+	uint16		hole_offset;
+	uint16		hole_length;
+
+	/* Buffer holding the rmgr-specific data associated with this block */
+	bool		has_data;
+	char	   *data;
+	uint16		data_len;
+	uint16		data_bufsz;
+} DecodedBkpBlock;
+
 struct XLogReaderState
 {
 	/* ----------------------------------------
@@ -79,6 +111,25 @@ struct XLogReaderState
 	XLogRecPtr	ReadRecPtr;		/* start of last record read */
 	XLogRecPtr	EndRecPtr;		/* end+1 of last record read */
 
+
+	/* ----------------------------------------
+	 * Decoded representation of current record
+	 *
+	 * Use XLogRecGet* functions to investigate the record; these fields
+	 * should not be accessed directly.
+	 * ----------------------------------------
+	 */
+	XLogRecord *decoded_record; /* currently decoded record */
+
+	char	   *main_data;		/* record's main data portion */
+	uint32		main_data_len;	/* main data portion's length */
+	uint32		main_data_bufsz;	/* allocated size of the buffer */
+
+	/* information about blocks referenced by the record. */
+	DecodedBkpBlock blocks[XLR_MAX_BLOCK_ID + 1];
+
+	int			max_block_id;	/* highest block_id in use (-1 if none) */
+
 	/* ----------------------------------------
 	 * private/internal state
 	 * ----------------------------------------
@@ -123,4 +174,28 @@ extern struct XLogRecord *XLogReadRecord(XLogReaderState *state,
 extern XLogRecPtr XLogFindNextRecord(XLogReaderState *state, XLogRecPtr RecPtr);
 #endif   /* FRONTEND */
 
+/* Functions for decoding an XLogRecord */
+
+extern bool DecodeXLogRecord(XLogReaderState *state, XLogRecord *record,
+				 char **errmsg);
+
+#define XLogRecGetTotalLen(decoder) ((decoder)->decoded_record->xl_tot_len)
+#define XLogRecGetPrev(decoder) ((decoder)->decoded_record->xl_prev)
+#define XLogRecGetInfo(decoder) ((decoder)->decoded_record->xl_info)
+#define XLogRecGetRmid(decoder) ((decoder)->decoded_record->xl_rmid)
+#define XLogRecGetXid(decoder) ((decoder)->decoded_record->xl_xid)
+#define XLogRecGetData(decoder) ((decoder)->main_data)
+#define XLogRecGetDataLen(decoder) ((decoder)->main_data_len)
+#define XLogRecHasAnyBlockRefs(decoder) ((decoder)->max_block_id >= 0)
+#define XLogRecHasBlockRef(decoder, block_id) \
+	((decoder)->blocks[block_id].in_use)
+#define XLogRecHasBlockImage(decoder, block_id) \
+	((decoder)->blocks[block_id].has_image)
+
+extern bool RestoreBlockImage(XLogReaderState *recoder, uint8 block_id, char *dst);
+extern char *XLogRecGetBlockData(XLogReaderState *record, uint8 block_id, Size *len);
+extern bool XLogRecGetBlockTag(XLogReaderState *record, uint8 block_id,
+				   RelFileNode *rnode, ForkNumber *forknum,
+				   BlockNumber *blknum);
+
 #endif   /* XLOGREADER_H */