Fix pg_xlogdump so that it handles cross-page XLP_FIRST_IS_CONTRECORD record.

Previously pg_xlogdump failed to dump the contents of the WAL file
if the file starts with the continuation WAL record which spans
more than one pages. Since pg_xlogdump assumed that the continuation
record always fits on a page, it could not find the valid WAL record to
start reading from in that case.

This patch changes pg_xlogdump so that it can handle a continuation
WAL record which crosses a page boundary and find the valid record
to start reading from.

Back-patch to 9.3 where pg_xlogdump was introduced.

Author: Pavan Deolasee
Reviewed-By: Michael Paquier and Craig Ringer
Discussion: CABOikdPsPByMiG6J01DKq6om2+BNkxHTPkOyqHM2a4oYwGKsqQ@mail.gmail.com

1 files changed, 64 insertions, 27 deletions

diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index 37cf9dee80f..0973d778ac9 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -844,46 +844,83 @@ XLogRecPtr
 XLogFindNextRecord(XLogReaderState *state, XLogRecPtr RecPtr)
 {
 	XLogReaderState saved_state = *state;
-	XLogRecPtr	targetPagePtr;
 	XLogRecPtr	tmpRecPtr;
-	int			targetRecOff;
 	XLogRecPtr	found = InvalidXLogRecPtr;
-	uint32		pageHeaderSize;
 	XLogPageHeader header;
-	int			readLen;
 	char	   *errormsg;
 
 	Assert(!XLogRecPtrIsInvalid(RecPtr));
 
-	targetRecOff = RecPtr % XLOG_BLCKSZ;
+	/*
+	 * skip over potential continuation data, keeping in mind that it may span
+	 * multiple pages
+	 */
+	tmpRecPtr = RecPtr;
+	while (true)
+	{
+		XLogRecPtr	targetPagePtr;
+		int			targetRecOff;
+		uint32		pageHeaderSize;
+		int			readLen;
 
-	/* scroll back to page boundary */
-	targetPagePtr = RecPtr - targetRecOff;
+		/*
+		 * Compute targetRecOff. It should typically be equal or greater than
+		 * short page-header since a valid record can't start anywhere before
+		 * that, except when caller has explicitly specified the offset that
+		 * falls somewhere there or when we are skipping multi-page
+		 * continuation record. It doesn't matter though because
+		 * ReadPageInternal() is prepared to handle that and will read at least
+		 * short page-header worth of data
+		 */
+		targetRecOff = tmpRecPtr % XLOG_BLCKSZ;
 
-	/* Read the page containing the record */
-	readLen = ReadPageInternal(state, targetPagePtr, targetRecOff);
-	if (readLen < 0)
-		goto err;
+		/* scroll back to page boundary */
+		targetPagePtr = tmpRecPtr - targetRecOff;
 
-	header = (XLogPageHeader) state->readBuf;
+		/* Read the page containing the record */
+		readLen = ReadPageInternal(state, targetPagePtr, targetRecOff);
+		if (readLen < 0)
+			goto err;
 
-	pageHeaderSize = XLogPageHeaderSize(header);
+		header = (XLogPageHeader) state->readBuf;
 
-	/* make sure we have enough data for the page header */
-	readLen = ReadPageInternal(state, targetPagePtr, pageHeaderSize);
-	if (readLen < 0)
-		goto err;
+		pageHeaderSize = XLogPageHeaderSize(header);
 
-	/* skip over potential continuation data */
-	if (header->xlp_info & XLP_FIRST_IS_CONTRECORD)
-	{
-		/* record headers are MAXALIGN'ed */
-		tmpRecPtr = targetPagePtr + pageHeaderSize
-			+ MAXALIGN(header->xlp_rem_len);
-	}
-	else
-	{
-		tmpRecPtr = targetPagePtr + pageHeaderSize;
+		/* make sure we have enough data for the page header */
+		readLen = ReadPageInternal(state, targetPagePtr, pageHeaderSize);
+		if (readLen < 0)
+			goto err;
+
+		/* skip over potential continuation data */
+		if (header->xlp_info & XLP_FIRST_IS_CONTRECORD)
+		{
+			/*
+			 * If the length of the remaining continuation data is more than
+			 * what can fit in this page, the continuation record crosses over
+			 * this page. Read the next page and try again. xlp_rem_len in the
+			 * next page header will contain the remaining length of the
+			 * continuation data
+			 *
+			 * Note that record headers are MAXALIGN'ed
+			 */
+			if (MAXALIGN(header->xlp_rem_len) > (XLOG_BLCKSZ - pageHeaderSize))
+				tmpRecPtr = targetPagePtr + XLOG_BLCKSZ;
+			else
+			{
+				/*
+				 * The previous continuation record ends in this page. Set
+				 * tmpRecPtr to point to the first valid record
+				 */
+				tmpRecPtr = targetPagePtr + pageHeaderSize
+					+ MAXALIGN(header->xlp_rem_len);
+				break;
+			}
+		}
+		else
+		{
+			tmpRecPtr = targetPagePtr + pageHeaderSize;
+			break;
+		}
 	}
 
 	/*