Add contrib/pg_walinspect.

Provides similar functionality to pg_waldump, but from a SQL interface
rather than a separate utility.

Author: Bharath Rupireddy
Reviewed-by: Greg Stark, Kyotaro Horiguchi, Andres Freund, Ashutosh Sharma, Nitin Jadhav, RKN Sai Krishna
Discussion: https://postgr.es/m/CALj2ACUGUYXsEQdKhEdsBzhGEyF3xggvLdD8C0VT72TNEfOiog%40mail.gmail.com

5 files changed, 257 insertions, 9 deletions

diff --git a/src/backend/access/rmgrdesc/xlogdesc.c b/src/backend/access/rmgrdesc/xlogdesc.c
index e7452af6790..dff1e7685e9 100644
--- a/src/backend/access/rmgrdesc/xlogdesc.c
+++ b/src/backend/access/rmgrdesc/xlogdesc.c
@@ -200,3 +200,133 @@ xlog_identify(uint8 info)
 
 	return id;
 }
+
+/*
+ * Returns a string giving information about all the blocks in an
+ * XLogRecord.
+ */
+void
+XLogRecGetBlockRefInfo(XLogReaderState *record, bool pretty,
+					   bool detailed_format, StringInfo buf,
+					   uint32 *fpi_len)
+{
+	int	block_id;
+
+	Assert(record != NULL);
+
+	if (detailed_format && pretty)
+		appendStringInfoChar(buf, '\n');
+
+	for (block_id = 0; block_id <= XLogRecMaxBlockId(record); block_id++)
+	{
+		RelFileNode rnode = {InvalidOid, InvalidOid, InvalidOid};
+		ForkNumber	forknum = InvalidForkNumber;
+		BlockNumber blk = InvalidBlockNumber;
+
+		if (!XLogRecHasBlockRef(record, block_id))
+			continue;
+
+		XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blk);
+
+		if (detailed_format)
+		{
+			/* Get block references in detailed format. */
+
+			if (pretty)
+				appendStringInfoChar(buf, '\t');
+			else if (block_id > 0)
+				appendStringInfoChar(buf, ' ');
+
+			appendStringInfo(buf,
+							 "blkref #%d: rel %u/%u/%u fork %s blk %u",
+							 block_id,
+							 rnode.spcNode, rnode.dbNode, rnode.relNode,
+							 forkNames[forknum],
+							 blk);
+
+			if (XLogRecHasBlockImage(record, block_id))
+			{
+				uint8		bimg_info = XLogRecGetBlock(record, block_id)->bimg_info;
+
+				/* Calculate the amount of FPI data in the record. */
+				if (fpi_len)
+					*fpi_len += XLogRecGetBlock(record, block_id)->bimg_len;
+
+				if (BKPIMAGE_COMPRESSED(bimg_info))
+				{
+					const char *method;
+
+					if ((bimg_info & BKPIMAGE_COMPRESS_PGLZ) != 0)
+						method = "pglz";
+					else if ((bimg_info & BKPIMAGE_COMPRESS_LZ4) != 0)
+						method = "lz4";
+					else if ((bimg_info & BKPIMAGE_COMPRESS_ZSTD) != 0)
+						method = "zstd";
+					else
+						method = "unknown";
+
+					appendStringInfo(buf,
+									 " (FPW%s); hole: offset: %u, length: %u, "
+									 "compression saved: %u, method: %s",
+									 XLogRecBlockImageApply(record, block_id) ?
+									 "" : " for WAL verification",
+									 XLogRecGetBlock(record, block_id)->hole_offset,
+									 XLogRecGetBlock(record, block_id)->hole_length,
+									 BLCKSZ -
+									 XLogRecGetBlock(record, block_id)->hole_length -
+									 XLogRecGetBlock(record, block_id)->bimg_len,
+									 method);
+				}
+				else
+				{
+					appendStringInfo(buf,
+									 " (FPW%s); hole: offset: %u, length: %u",
+									 XLogRecBlockImageApply(record, block_id) ?
+									 "" : " for WAL verification",
+									 XLogRecGetBlock(record, block_id)->hole_offset,
+									 XLogRecGetBlock(record, block_id)->hole_length);
+				}
+			}
+
+			if (pretty)
+				appendStringInfoChar(buf, '\n');
+		}
+		else
+		{
+			/* Get block references in short format. */
+
+			if (forknum != MAIN_FORKNUM)
+			{
+				appendStringInfo(buf,
+								 ", blkref #%d: rel %u/%u/%u fork %s blk %u",
+								 block_id,
+								 rnode.spcNode, rnode.dbNode, rnode.relNode,
+								 forkNames[forknum],
+								 blk);
+			}
+			else
+			{
+				appendStringInfo(buf,
+								 ", blkref #%d: rel %u/%u/%u blk %u",
+								 block_id,
+								 rnode.spcNode, rnode.dbNode, rnode.relNode,
+								 blk);
+			}
+
+			if (XLogRecHasBlockImage(record, block_id))
+			{
+				/* Calculate the amount of FPI data in the record. */
+				if (fpi_len)
+					*fpi_len += XLogRecGetBlock(record, block_id)->bimg_len;
+
+				if (XLogRecBlockImageApply(record, block_id))
+					appendStringInfo(buf, " FPW");
+				else
+					appendStringInfo(buf, " FPW for WAL verification");
+			}
+		}
+	}
+
+	if (!detailed_format && pretty)
+		appendStringInfoChar(buf, '\n');
+}
diff --git a/src/backend/access/transam/Makefile b/src/backend/access/transam/Makefile
index 8c17c88dfc4..3e5444a6f76 100644
--- a/src/backend/access/transam/Makefile
+++ b/src/backend/access/transam/Makefile
@@ -34,6 +34,7 @@ OBJS = \
 	xlogprefetcher.o \
 	xlogreader.o \
 	xlogrecovery.o \
+	xlogstats.o \
 	xlogutils.o
 
 include $(top_srcdir)/src/backend/common.mk
diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index 5862d9dc75f..a5f1a648d3d 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -1320,13 +1320,6 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 	return true;
 }
 
-#ifdef FRONTEND
-/*
- * Functions that are currently not needed in the backend, but are better
- * implemented inside xlogreader.c because of the internal facilities available
- * here.
- */
-
 /*
  * Find the first record with an lsn >= RecPtr.
  *
@@ -1447,8 +1440,6 @@ err:
 	return InvalidXLogRecPtr;
 }
 
-#endif							/* FRONTEND */
-
 /*
  * Helper function to ease writing of XLogRoutine->page_read callbacks.
  * If this function is used, caller must supply a segment_open callback in
diff --git a/src/backend/access/transam/xlogstats.c b/src/backend/access/transam/xlogstats.c
new file mode 100644
index 00000000000..aff3069ecba
--- /dev/null
+++ b/src/backend/access/transam/xlogstats.c
@@ -0,0 +1,93 @@
+/*-------------------------------------------------------------------------
+ *
+ * xlogstats.c
+ *		Functions for WAL Statitstics
+ *
+ * Copyright (c) 2022, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/backend/access/transam/xlogstats.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/xlogreader.h"
+#include "access/xlogstats.h"
+
+/*
+ * Calculate the size of a record, split into !FPI and FPI parts.
+ */
+void
+XLogRecGetLen(XLogReaderState *record, uint32 *rec_len,
+			  uint32 *fpi_len)
+{
+	int	block_id;
+
+	/*
+	 * Calculate the amount of FPI data in the record.
+	 *
+	 * XXX: We peek into xlogreader's private decoded backup blocks for the
+	 * bimg_len indicating the length of FPI data.
+	 */
+	*fpi_len = 0;
+	for (block_id = 0; block_id <= XLogRecMaxBlockId(record); block_id++)
+	{
+		if (XLogRecHasBlockImage(record, block_id))
+			*fpi_len += XLogRecGetBlock(record, block_id)->bimg_len;
+	}
+
+	/*
+	 * Calculate the length of the record as the total length - the length of
+	 * all the block images.
+	 */
+	*rec_len = XLogRecGetTotalLen(record) - *fpi_len;
+}
+
+/*
+ * Store per-rmgr and per-record statistics for a given record.
+ */
+void
+XLogRecStoreStats(XLogStats *stats, XLogReaderState *record)
+{
+	RmgrId	rmid;
+	uint8	recid;
+	uint32	rec_len;
+	uint32	fpi_len;
+
+	Assert(stats != NULL && record != NULL);
+
+	stats->count++;
+
+	rmid = XLogRecGetRmid(record);
+
+	XLogRecGetLen(record, &rec_len, &fpi_len);
+
+	/* Update per-rmgr statistics */
+
+	stats->rmgr_stats[rmid].count++;
+	stats->rmgr_stats[rmid].rec_len += rec_len;
+	stats->rmgr_stats[rmid].fpi_len += fpi_len;
+
+	/*
+	 * Update per-record statistics, where the record is identified by a
+	 * combination of the RmgrId and the four bits of the xl_info field that
+	 * are the rmgr's domain (resulting in sixteen possible entries per
+	 * RmgrId).
+	 */
+
+	recid = XLogRecGetInfo(record) >> 4;
+
+	/*
+	 * XACT records need to be handled differently. Those records use the
+	 * first bit of those four bits for an optional flag variable and the
+	 * following three bits for the opcode. We filter opcode out of xl_info
+	 * and use it as the identifier of the record.
+	 */
+	if (rmid == RM_XACT_ID)
+		recid &= 0x07;
+
+	stats->record_stats[rmid][recid].count++;
+	stats->record_stats[rmid][recid].rec_len += rec_len;
+	stats->record_stats[rmid][recid].fpi_len += fpi_len;
+}
diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c
index bb2d3ec991c..b5d34c61e66 100644
--- a/src/backend/access/transam/xlogutils.c
+++ b/src/backend/access/transam/xlogutils.c
@@ -80,6 +80,10 @@ typedef struct xl_invalid_page
 
 static HTAB *invalid_page_tab = NULL;
 
+static int
+read_local_xlog_page_guts(XLogReaderState *state, XLogRecPtr targetPagePtr,
+						  int reqLen, XLogRecPtr targetRecPtr,
+						  char *cur_page, bool wait_for_wal);
 
 /* Report a reference to an invalid page */
 static void
@@ -871,6 +875,31 @@ int
 read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 					 int reqLen, XLogRecPtr targetRecPtr, char *cur_page)
 {
+	return read_local_xlog_page_guts(state, targetPagePtr, reqLen,
+									 targetRecPtr, cur_page, true);
+}
+
+/*
+ * Same as read_local_xlog_page except that it doesn't wait for future WAL
+ * to be available.
+ */
+int
+read_local_xlog_page_no_wait(XLogReaderState *state, XLogRecPtr targetPagePtr,
+							 int reqLen, XLogRecPtr targetRecPtr,
+							 char *cur_page)
+{
+	return read_local_xlog_page_guts(state, targetPagePtr, reqLen,
+									 targetRecPtr, cur_page, false);
+}
+
+/*
+ * Implementation of read_local_xlog_page and its no wait version.
+ */
+static int
+read_local_xlog_page_guts(XLogReaderState *state, XLogRecPtr targetPagePtr,
+						  int reqLen, XLogRecPtr targetRecPtr,
+						  char *cur_page, bool wait_for_wal)
+{
 	XLogRecPtr	read_upto,
 				loc;
 	TimeLineID	tli;
@@ -925,6 +954,10 @@ read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 			if (loc <= read_upto)
 				break;
 
+			/* If asked, let's not wait for future WAL. */
+			if (!wait_for_wal)
+				break;
+
 			CHECK_FOR_INTERRUPTS();
 			pg_usleep(1000L);
 		}