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, 15 insertions, 16 deletions

diff --git a/src/include/access/gist_private.h b/src/include/access/gist_private.h
index 21daf3b2b6a..2cbc918ad1a 100644
--- a/src/include/access/gist_private.h
+++ b/src/include/access/gist_private.h
@@ -16,7 +16,7 @@
 
 #include "access/gist.h"
 #include "access/itup.h"
-#include "access/xlogrecord.h"
+#include "access/xlogreader.h"
 #include "fmgr.h"
 #include "storage/bufmgr.h"
 #include "storage/buffile.h"
@@ -185,34 +185,33 @@ typedef GISTScanOpaqueData *GISTScanOpaque;
 #define XLOG_GIST_CREATE_INDEX		0x50
  /* #define XLOG_GIST_PAGE_DELETE		 0x60 */	/* not used anymore */
 
+/*
+ * Backup Blk 0: updated page.
+ * Backup Blk 1: If this operation completes a page split, by inserting a
+ *				 downlink for the split page, the left half of the split
+ */
 typedef struct gistxlogPageUpdate
 {
-	RelFileNode node;
-	BlockNumber blkno;
-
-	/*
-	 * If this operation completes a page split, by inserting a downlink for
-	 * the split page, leftchild points to the left half of the split.
-	 */
-	BlockNumber leftchild;
-
 	/* number of deleted offsets */
 	uint16		ntodelete;
+	uint16		ntoinsert;
 
 	/*
-	 * follow: 1. todelete OffsetNumbers 2. tuples to insert
+	 * In payload of blk 0 : 1. todelete OffsetNumbers 2. tuples to insert
 	 */
 } gistxlogPageUpdate;
 
+/*
+ * Backup Blk 0: If this operation completes a page split, by inserting a
+ *				 downlink for the split page, the left half of the split
+ * Backup Blk 1 - npage: split pages (1 is the original page)
+ */
 typedef struct gistxlogPageSplit
 {
-	RelFileNode node;
-	BlockNumber origblkno;		/* splitted page */
 	BlockNumber origrlink;		/* rightlink of the page before split */
 	GistNSN		orignsn;		/* NSN of the page before split */
 	bool		origleaf;		/* was splitted page a leaf page? */
 
-	BlockNumber leftchild;		/* like in gistxlogPageUpdate */
 	uint16		npage;			/* # of pages in the split */
 	bool		markfollowright;	/* set F_FOLLOW_RIGHT flags */
 
@@ -451,8 +450,8 @@ extern SplitedPageLayout *gistSplit(Relation r, Page page, IndexTuple *itup,
 		  int len, GISTSTATE *giststate);
 
 /* gistxlog.c */
-extern void gist_redo(XLogRecPtr lsn, XLogRecord *record);
-extern void gist_desc(StringInfo buf, XLogRecord *record);
+extern void gist_redo(XLogReaderState *record);
+extern void gist_desc(StringInfo buf, XLogReaderState *record);
 extern const char *gist_identify(uint8 info);
 extern void gist_xlog_startup(void);
 extern void gist_xlog_cleanup(void);