v17-0002-pg_walinspect.patch

From 064f7f5c304558510b0f1769a6114df6eb98e55d Mon Sep 17 00:00:00 2001
From: Bharath Rupireddy <bharath.rupireddyforpostgres@gmail.com>
Date: Wed, 6 Apr 2022 07:56:10 +0000
Subject: [PATCH v17] pg_walinspect

---
 contrib/Makefile                             |   1 +
 contrib/pg_walinspect/.gitignore             |   4 +
 contrib/pg_walinspect/Makefile               |  26 +
 contrib/pg_walinspect/pg_walinspect--1.0.sql | 118 ++++
 contrib/pg_walinspect/pg_walinspect.c        | 639 +++++++++++++++++++
 contrib/pg_walinspect/pg_walinspect.control  |   5 +
 src/backend/access/transam/xlogreader.c      |  13 +-
 src/backend/access/transam/xlogutils.c       |  33 +
 src/bin/pg_waldump/pg_waldump.c              |   5 +
 src/include/access/xlog.h                    |   2 +-
 src/include/access/xlog_internal.h           |   2 +-
 src/include/access/xlogreader.h              |   2 -
 src/include/access/xlogutils.h               |   4 +
 13 files changed, 843 insertions(+), 11 deletions(-)
 create mode 100644 contrib/pg_walinspect/.gitignore
 create mode 100644 contrib/pg_walinspect/Makefile
 create mode 100644 contrib/pg_walinspect/pg_walinspect--1.0.sql
 create mode 100644 contrib/pg_walinspect/pg_walinspect.c
 create mode 100644 contrib/pg_walinspect/pg_walinspect.control

diff --git a/contrib/Makefile b/contrib/Makefile
index 332b486ecc..bbf220407b 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -41,6 +41,7 @@ SUBDIRS = \
 		pgrowlocks	\
 		pgstattuple	\
 		pg_visibility	\
+		pg_walinspect	\
 		postgres_fdw	\
 		seg		\
 		spi		\
diff --git a/contrib/pg_walinspect/.gitignore b/contrib/pg_walinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_walinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_walinspect/Makefile b/contrib/pg_walinspect/Makefile
new file mode 100644
index 0000000000..c92a97447f
--- /dev/null
+++ b/contrib/pg_walinspect/Makefile
@@ -0,0 +1,26 @@
+# contrib/pg_walinspect/Makefile
+
+MODULE_big = pg_walinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_walinspect.o
+PGFILEDESC = "pg_walinspect - functions to inspect contents of PostgreSQL Write-Ahead Log"
+
+PG_CPPFLAGS = -I$(libpq_srcdir)
+SHLIB_LINK_INTERNAL = $(libpq)
+
+EXTENSION = pg_walinspect
+DATA = pg_walinspect--1.0.sql
+
+REGRESS = pg_walinspect
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_walinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_walinspect/pg_walinspect--1.0.sql b/contrib/pg_walinspect/pg_walinspect--1.0.sql
new file mode 100644
index 0000000000..aae6456c18
--- /dev/null
+++ b/contrib/pg_walinspect/pg_walinspect--1.0.sql
@@ -0,0 +1,118 @@
+/* contrib/pg_walinspect/pg_walinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_walinspect" to load this file. \quit
+
+--
+-- pg_get_wal_record_info()
+--
+CREATE FUNCTION pg_get_wal_record_info(IN in_lsn pg_lsn,
+    OUT start_lsn pg_lsn,
+    OUT end_lsn pg_lsn,
+    OUT prev_lsn pg_lsn,
+    OUT xid xid,
+    OUT resource_manager text,
+    OUT record_type text,
+    OUT record_length int4,
+    OUT main_data_length int4,
+    OUT fpi_length int4,
+	OUT description text,
+    OUT block_ref text
+)
+AS 'MODULE_PATHNAME', 'pg_get_wal_record_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_wal_record_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_wal_record_info(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_wal_records_info()
+--
+CREATE FUNCTION pg_get_wal_records_info(IN start_lsn pg_lsn,
+    IN end_lsn pg_lsn,
+    OUT start_lsn pg_lsn,
+    OUT end_lsn pg_lsn,
+    OUT prev_lsn pg_lsn,
+    OUT xid xid,
+    OUT resource_manager text,
+    OUT record_type text,
+    OUT record_length int4,
+    OUT main_data_length int4,
+    OUT fpi_length int4,
+	OUT description text,
+    OUT block_ref text
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME', 'pg_get_wal_records_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_wal_records_info(pg_lsn, pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_wal_records_info(pg_lsn, pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_wal_records_info_till_end_of_wal()
+--
+CREATE FUNCTION pg_get_wal_records_info_till_end_of_wal(IN start_lsn pg_lsn,
+    OUT start_lsn pg_lsn,
+    OUT end_lsn pg_lsn,
+    OUT prev_lsn pg_lsn,
+    OUT xid xid,
+    OUT resource_manager text,
+    OUT record_type text,
+    OUT record_length int4,
+    OUT main_data_length int4,
+    OUT fpi_length int4,
+	OUT description text,
+    OUT block_ref text
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME', 'pg_get_wal_records_info_till_end_of_wal'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_wal_records_info_till_end_of_wal(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_wal_records_info_till_end_of_wal(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_wal_stats()
+--
+CREATE FUNCTION pg_get_wal_stats(IN start_lsn pg_lsn,
+    IN end_lsn pg_lsn,
+    IN  per_record boolean DEFAULT false,
+    OUT "resource_manager/record_type" text,
+    OUT count int8,
+    OUT count_percentage float4,
+    OUT record_size int8,
+    OUT record_size_percentage float4,
+    OUT fpi_size int8,
+    OUT fpi_size_percentage float4,
+    OUT combined_size int8,
+    OUT combined_size_percentage float4
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME', 'pg_get_wal_stats'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_wal_stats(pg_lsn, pg_lsn, boolean) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_wal_stats(pg_lsn, pg_lsn, boolean) TO pg_read_server_files;
+
+--
+-- pg_get_wal_stats_till_end_of_wal()
+--
+CREATE FUNCTION pg_get_wal_stats_till_end_of_wal(IN start_lsn pg_lsn,
+    IN  per_record boolean DEFAULT false,
+    OUT "resource_manager/record_type" text,
+    OUT count int8,
+    OUT count_percentage float4,
+    OUT record_size int8,
+    OUT record_size_percentage float4,
+    OUT fpi_size int8,
+    OUT fpi_size_percentage float4,
+    OUT combined_size int8,
+    OUT combined_size_percentage float4
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME', 'pg_get_wal_stats_till_end_of_wal'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_wal_stats_till_end_of_wal(pg_lsn, boolean) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_wal_stats_till_end_of_wal(pg_lsn, boolean) TO pg_read_server_files;
diff --git a/contrib/pg_walinspect/pg_walinspect.c b/contrib/pg_walinspect/pg_walinspect.c
new file mode 100644
index 0000000000..b93e16752c
--- /dev/null
+++ b/contrib/pg_walinspect/pg_walinspect.c
@@ -0,0 +1,639 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_walinspect.c
+ *		  Functions to inspect contents of PostgreSQL Write-Ahead Log
+ *
+ * Copyright (c) 2022, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_walinspect/pg_walinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/xlog.h"
+#include "access/xlog_internal.h"
+#include "access/xlogreader.h"
+#include "access/xlogrecovery.h"
+#include "access/xlogstats.h"
+#include "access/xlogutils.h"
+#include "funcapi.h"
+#include "miscadmin.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_waldump tool as well.
+ */
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_wal_record_info);
+PG_FUNCTION_INFO_V1(pg_get_wal_records_info);
+PG_FUNCTION_INFO_V1(pg_get_wal_records_info_till_end_of_wal);
+PG_FUNCTION_INFO_V1(pg_get_wal_stats);
+PG_FUNCTION_INFO_V1(pg_get_wal_stats_till_end_of_wal);
+
+/*
+ * Struct holding information about the parameters that can be passed to
+ * GetWalStats.
+ */
+typedef struct GetWalStatsParams
+{
+	/* If true, generate statistics per-record instead of per-rmgr. */
+	bool stats_per_record;
+} GetWalStatsParams;
+
+typedef void (*GetWALDetailsCB) (FunctionCallInfo fcinfo,
+								 XLogRecPtr start_lsn,
+								 XLogRecPtr end_lsn,
+								 void *params);
+
+static bool IsFutureLSN(XLogRecPtr lsn, XLogRecPtr *curr_lsn);
+static XLogReaderState *InitXLogReaderState(XLogRecPtr lsn,
+											XLogRecPtr *first_record);
+static XLogRecord *ReadNextXLogRecord(XLogReaderState *xlogreader,
+									  XLogRecPtr first_record);
+static void GetWALRecordInfo(XLogReaderState *record, XLogRecPtr lsn,
+							 Datum *values, bool *nulls, uint32 ncols);
+static void GetWALDetailsGuts(FunctionCallInfo fcinfo, bool till_end_of_wal,
+							  GetWALDetailsCB wal_details_cb);
+static void GetWALRecordsInfo(FunctionCallInfo fcinfo, XLogRecPtr start_lsn,
+							  XLogRecPtr end_lsn, void *params);
+static void GetXLogSummaryStats(XLogStats * stats, ReturnSetInfo *rsinfo,
+								Datum *values, bool *nulls, uint32 ncols,
+								bool stats_per_record);
+static void FillXLogStatsRow(const char *name, uint64 n, uint64 total_count,
+							 uint64 rec_len, uint64 total_rec_len,
+							 uint64 fpi_len, uint64 total_fpi_len,
+							 uint64 tot_len, uint64 total_len,
+							 Datum *values, bool *nulls, uint32 ncols);
+static void GetWalStats(FunctionCallInfo fcinfo, XLogRecPtr start_lsn,
+						XLogRecPtr end_lsn, void *params);
+
+/*
+ * Check if the given LSN is in future. Also, return the LSN up to which the
+ * server has WAL.
+ */
+static bool
+IsFutureLSN(XLogRecPtr lsn, XLogRecPtr *curr_lsn)
+{
+	/*
+	 * We determine the current LSN of the server similar to how page_read
+	 * callback read_local_xlog_page_no_wait does.
+	 */
+	if (!RecoveryInProgress())
+		*curr_lsn = GetFlushRecPtr(NULL);
+	else
+		*curr_lsn = GetXLogReplayRecPtr(NULL);
+
+	Assert(!XLogRecPtrIsInvalid(*curr_lsn));
+
+	if (lsn >= *curr_lsn)
+		return true;
+
+	return false;
+}
+
+/*
+ * Intialize WAL reader and identify first valid LSN.
+ */
+static XLogReaderState *
+InitXLogReaderState(XLogRecPtr lsn, XLogRecPtr *first_record)
+{
+	XLogReaderState *xlogreader;
+
+	/*
+	 * Reading WAL below the first page of the first sgements isn't allowed.
+	 * This is a bootstrap WAL page and the page_read callback fails to read
+	 * it.
+	 */
+	if (lsn < XLOG_BLCKSZ)
+		ereport(ERROR,
+				(errmsg("could not read WAL at LSN %X/%X",
+						LSN_FORMAT_ARGS(lsn))));
+
+	xlogreader = XLogReaderAllocate(wal_segment_size, NULL,
+									XL_ROUTINE(.page_read = &read_local_xlog_page_no_wait,
+											   .segment_open = &wal_segment_open,
+											   .segment_close = &wal_segment_close),
+									NULL);
+
+	if (xlogreader == NULL)
+		ereport(ERROR,
+				(errcode(ERRCODE_OUT_OF_MEMORY),
+				 errmsg("out of memory"),
+				 errdetail("Failed while allocating a WAL reading processor.")));
+
+	/* First find a valid recptr to start from. */
+	*first_record = XLogFindNextRecord(xlogreader, lsn);
+
+	if (XLogRecPtrIsInvalid(*first_record))
+		ereport(ERROR,
+				(errmsg("could not find a valid record after %X/%X",
+						LSN_FORMAT_ARGS(lsn))));
+
+	return xlogreader;
+}
+
+/*
+ * Read next WAL record.
+ */
+static XLogRecord *
+ReadNextXLogRecord(XLogReaderState *xlogreader, XLogRecPtr first_record)
+{
+	XLogRecord *record;
+	char	*errormsg;
+
+	record = XLogReadRecord(xlogreader, &errormsg);
+
+	if (record == NULL)
+	{
+		if (errormsg)
+			ereport(ERROR,
+					(errcode_for_file_access(),
+					 errmsg("could not read WAL at %X/%X: %s",
+							LSN_FORMAT_ARGS(first_record), errormsg)));
+		else
+			ereport(ERROR,
+					(errcode_for_file_access(),
+					 errmsg("could not read WAL at %X/%X",
+							LSN_FORMAT_ARGS(first_record))));
+	}
+
+	return record;
+}
+
+/*
+ * Get a single WAL record info.
+ */
+static void
+GetWALRecordInfo(XLogReaderState *record, XLogRecPtr lsn,
+				 Datum *values, bool *nulls, uint32 ncols)
+{
+	const char *id;
+	const RmgrData *desc;
+	uint32	fpi_len = 0;
+	StringInfoData rec_desc;
+	StringInfoData rec_blk_ref;
+	uint32	main_data_len;
+	int	i = 0;
+
+	desc = &RmgrTable[XLogRecGetRmid(record)];
+	id = desc->rm_identify(XLogRecGetInfo(record));
+
+	if (id == NULL)
+		id = psprintf("UNKNOWN (%x)", XLogRecGetInfo(record) & ~XLR_INFO_MASK);
+
+	initStringInfo(&rec_desc);
+	desc->rm_desc(&rec_desc, record);
+
+	/* Block references. */
+	initStringInfo(&rec_blk_ref);
+	XLogRecGetBlockRefInfo(record, NULL, &fpi_len, true, &rec_blk_ref);
+
+	main_data_len = XLogRecGetDataLen(record);
+
+	values[i++] = LSNGetDatum(lsn);
+	values[i++] = LSNGetDatum(record->EndRecPtr - 1);
+	values[i++] = LSNGetDatum(XLogRecGetPrev(record));
+	values[i++] = TransactionIdGetDatum(XLogRecGetXid(record));
+	values[i++] = CStringGetTextDatum(desc->rm_name);
+	values[i++] = CStringGetTextDatum(id);
+	values[i++] = UInt32GetDatum(XLogRecGetTotalLen(record));
+	values[i++] = UInt32GetDatum(main_data_len);
+	values[i++] = UInt32GetDatum(fpi_len);
+	values[i++] = CStringGetTextDatum(rec_desc.data);
+	values[i++] = CStringGetTextDatum(rec_blk_ref.data);
+
+	Assert(i == ncols);
+}
+
+/*
+ * Get WAL record info.
+ *
+ * This function emits an error if a future WAL LSN i.e. WAL LSN the database
+ * system doesn't know about is specified.
+ */
+Datum
+pg_get_wal_record_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_WAL_RECORD_INFO_COLS 11
+	Datum	result;
+	Datum	values[PG_GET_WAL_RECORD_INFO_COLS];
+	bool	nulls[PG_GET_WAL_RECORD_INFO_COLS];
+	XLogRecPtr	lsn;
+	XLogRecPtr	curr_lsn;
+	XLogRecPtr	first_record;
+	XLogReaderState *xlogreader;
+	TupleDesc	tupdesc;
+	HeapTuple	tuple;
+
+	lsn = PG_GETARG_LSN(0);
+
+	if (IsFutureLSN(lsn, &curr_lsn))
+	{
+		/*
+		 * GetFlushRecPtr or GetXLogReplayRecPtr gives "end+1" LSN of the last
+		 * record flushed or replayed respectively. But let's use the LSN up
+		 * to "end" in user facing message.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("cannot accept future input LSN"),
+				 errdetail("Last WAL record on the database system ends at LSN %X/%X.",
+						   LSN_FORMAT_ARGS(curr_lsn - 1))));
+	}
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	xlogreader = InitXLogReaderState(lsn, &first_record);
+
+	Assert(xlogreader);
+
+	(void) ReadNextXLogRecord(xlogreader, first_record);
+
+	MemSet(values, 0, sizeof(values));
+	MemSet(nulls, 0, sizeof(nulls));
+
+	GetWALRecordInfo(xlogreader, first_record, values, nulls,
+					 PG_GET_WAL_RECORD_INFO_COLS);
+
+	XLogReaderFree(xlogreader);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+	result = HeapTupleGetDatum(tuple);
+
+	PG_RETURN_DATUM(result);
+#undef PG_GET_WAL_RECORD_INFO_COLS
+}
+
+/*
+ * Get WAL details such as record info, stats using the passed in callback.
+ */
+static void
+GetWALDetailsGuts(FunctionCallInfo fcinfo, bool till_end_of_wal,
+				  GetWALDetailsCB wal_details_cb)
+{
+	XLogRecPtr	start_lsn;
+	XLogRecPtr	end_lsn;
+	XLogRecPtr	curr_lsn;
+	GetWalStatsParams stats_params;
+
+	start_lsn = PG_GETARG_LSN(0);
+
+	/* If not till end of wal, end_lsn would have been specified. */
+	if (!till_end_of_wal)
+		end_lsn = PG_GETARG_LSN(1);
+
+	if (IsFutureLSN(start_lsn, &curr_lsn))
+	{
+		/*
+		 * GetFlushRecPtr or GetXLogReplayRecPtr gives "end+1" LSN of the last
+		 * record flushed or replayed respectively. But let's use the LSN up
+		 * to "end" in user facing message.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("cannot accept future start LSN"),
+				 errdetail("Last WAL record on the database system ends at LSN %X/%X.",
+						   LSN_FORMAT_ARGS(curr_lsn - 1))));
+	}
+
+	if (!till_end_of_wal && end_lsn >= curr_lsn)
+	{
+		/*
+		 * GetFlushRecPtr or GetXLogReplayRecPtr gives "end+1" LSN of the last
+		 * record flushed or replayed respectively. But let's use the LSN up
+		 * to "end" in user facing message.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("cannot accept future end LSN"),
+				 errdetail("Last WAL record on the database system ends at LSN %X/%X.",
+						   LSN_FORMAT_ARGS(curr_lsn - 1))));
+	}
+	else if (till_end_of_wal)
+	{
+		/*
+		 * GetFlushRecPtr or GetXLogReplayRecPtr gives "end+1" LSN of the last
+		 * record flushed or replayed respectively. But let's use the LSN up to
+		 * "end".
+		 */
+		end_lsn = curr_lsn - 1;
+	}
+
+	if (start_lsn >= end_lsn)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("WAL start LSN must be less than end LSN")));
+
+	if (wal_details_cb == GetWalStats)
+	{
+		MemSet(&stats_params, 0, sizeof(GetWalStatsParams));
+
+		if (!till_end_of_wal)
+			stats_params.stats_per_record = PG_GETARG_BOOL(2);
+		else
+			stats_params.stats_per_record = PG_GETARG_BOOL(1);
+
+		wal_details_cb(fcinfo, start_lsn, end_lsn, (void *) &stats_params);
+	}
+	else if (wal_details_cb == GetWALRecordsInfo)
+	{
+		wal_details_cb(fcinfo, start_lsn, end_lsn, NULL);
+	}
+}
+
+/*
+ * Get info and data of all WAL records between start LSN and end LSN.
+ */
+static void
+GetWALRecordsInfo(FunctionCallInfo fcinfo, XLogRecPtr start_lsn,
+				  XLogRecPtr end_lsn, void *params)
+{
+#define PG_GET_WAL_RECORDS_INFO_COLS 11
+	XLogRecPtr	first_record;
+	XLogReaderState *xlogreader;
+	ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+	Datum	values[PG_GET_WAL_RECORDS_INFO_COLS];
+	bool	nulls[PG_GET_WAL_RECORDS_INFO_COLS];
+
+	SetSingleFuncCall(fcinfo, 0);
+
+	xlogreader = InitXLogReaderState(start_lsn, &first_record);
+
+	Assert(xlogreader);
+
+	MemSet(values, 0, sizeof(values));
+	MemSet(nulls, 0, sizeof(nulls));
+
+	for (;;)
+	{
+		(void) ReadNextXLogRecord(xlogreader, first_record);
+
+		/*
+		 * Let's not show the record info if it is spanning more than the
+		 * end_lsn. EndRecPtr is "end+1" of the last read record, hence
+		 * use "end" here.
+		 */
+		if ((xlogreader->EndRecPtr - 1) <= end_lsn)
+		{
+			GetWALRecordInfo(xlogreader, xlogreader->currRecPtr, values, nulls,
+							 PG_GET_WAL_RECORDS_INFO_COLS);
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+
+		/* Exit loop if read up to end_lsn. */
+		if (xlogreader->EndRecPtr >= end_lsn)
+			break;
+
+		CHECK_FOR_INTERRUPTS();
+	}
+
+	XLogReaderFree(xlogreader);
+
+#undef PG_GET_WAL_RECORDS_INFO_COLS
+}
+
+/*
+ * Get info and data of all WAL records between start LSN and end LSN.
+ *
+ * This function emits an error if a future start or end WAL LSN i.e. WAL LSN
+ * the database system doesn't know about is specified.
+ */
+Datum
+pg_get_wal_records_info(PG_FUNCTION_ARGS)
+{
+	GetWALDetailsGuts(fcinfo, false, GetWALRecordsInfo);
+
+	PG_RETURN_VOID();
+}
+
+/*
+ * Get info and data of all WAL records from start LSN till end of WAL.
+ *
+ * This function emits an error if a future start i.e. WAL LSN the database
+ * system doesn't know about is specified.
+ */
+Datum
+pg_get_wal_records_info_till_end_of_wal(PG_FUNCTION_ARGS)
+{
+	GetWALDetailsGuts(fcinfo, true, GetWALRecordsInfo);
+
+	PG_RETURN_VOID();
+}
+
+/*
+ * Fill single row of record counts and sizes for an rmgr or record.
+ */
+static void
+FillXLogStatsRow(const char *name,
+				 uint64 n, uint64 total_count,
+				 uint64 rec_len, uint64 total_rec_len,
+				 uint64 fpi_len, uint64 total_fpi_len,
+				 uint64 tot_len, uint64 total_len,
+				 Datum *values, bool *nulls, uint32 ncols)
+{
+	double	n_pct,
+			rec_len_pct,
+			fpi_len_pct,
+			tot_len_pct;
+	int	i = 0;
+
+	n_pct = 0;
+	if (total_count != 0)
+		n_pct = 100 * (double) n / total_count;
+
+	rec_len_pct = 0;
+	if (total_rec_len != 0)
+		rec_len_pct = 100 * (double) rec_len / total_rec_len;
+
+	fpi_len_pct = 0;
+	if (total_fpi_len != 0)
+		fpi_len_pct = 100 * (double) fpi_len / total_fpi_len;
+
+	tot_len_pct = 0;
+	if (total_len != 0)
+		tot_len_pct = 100 * (double) tot_len / total_len;
+
+	values[i++] = CStringGetTextDatum(name);
+	values[i++] = Int64GetDatum(n);
+	values[i++] = Float4GetDatum(n_pct);
+	values[i++] = Int64GetDatum(rec_len);
+	values[i++] = Float4GetDatum(rec_len_pct);
+	values[i++] = Int64GetDatum(fpi_len);
+	values[i++] = Float4GetDatum(fpi_len_pct);
+	values[i++] = Int64GetDatum(tot_len);
+	values[i++] = Float4GetDatum(tot_len_pct);
+
+	Assert(i == ncols);
+}
+
+/*
+ * Get summary statistics about the records seen so far.
+ */
+static void
+GetXLogSummaryStats(XLogStats *stats, ReturnSetInfo *rsinfo,
+					Datum *values, bool *nulls, uint32 ncols,
+					bool stats_per_record)
+{
+	uint64	total_count = 0;
+	uint64	total_rec_len = 0;
+	uint64	total_fpi_len = 0;
+	uint64	total_len = 0;
+	int	ri;
+
+	/*
+	 * Each row shows its percentages of the total, so make a first pass to
+	 * calculate column totals.
+	 */
+	for (ri = 0; ri < RM_NEXT_ID; ri++)
+	{
+		total_count += stats->rmgr_stats[ri].count;
+		total_rec_len += stats->rmgr_stats[ri].rec_len;
+		total_fpi_len += stats->rmgr_stats[ri].fpi_len;
+	}
+	total_len = total_rec_len + total_fpi_len;
+
+	for (ri = 0; ri < RM_NEXT_ID; ri++)
+	{
+		uint64		count;
+		uint64		rec_len;
+		uint64		fpi_len;
+		uint64		tot_len;
+		const RmgrData *desc = &RmgrTable[ri];
+
+		if (stats_per_record)
+		{
+			int rj;
+
+			for (rj = 0; rj < MAX_XLINFO_TYPES; rj++)
+			{
+				const char *id;
+
+				count = stats->record_stats[ri][rj].count;
+				rec_len = stats->record_stats[ri][rj].rec_len;
+				fpi_len = stats->record_stats[ri][rj].fpi_len;
+				tot_len = rec_len + fpi_len;
+
+				/* Skip undefined combinations and ones that didn't occur */
+				if (count == 0)
+					continue;
+
+				/* the upper four bits in xl_info are the rmgr's */
+				id = desc->rm_identify(rj << 4);
+				if (id == NULL)
+					id = psprintf("UNKNOWN (%x)", rj << 4);
+
+				FillXLogStatsRow(psprintf("%s/%s", desc->rm_name, id), count,
+								 total_count, rec_len, total_rec_len, fpi_len,
+								 total_fpi_len, tot_len, total_len,
+								 values, nulls, ncols);
+
+				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+									 values, nulls);
+			}
+		}
+		else
+		{
+			count = stats->rmgr_stats[ri].count;
+			rec_len = stats->rmgr_stats[ri].rec_len;
+			fpi_len = stats->rmgr_stats[ri].fpi_len;
+			tot_len = rec_len + fpi_len;
+
+			FillXLogStatsRow(desc->rm_name, count, total_count, rec_len,
+							 total_rec_len, fpi_len, total_fpi_len, tot_len,
+							 total_len, values, nulls, ncols);
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+}
+
+/*
+ * Get WAL stats between start LSN and end LSN.
+ */
+static void
+GetWalStats(FunctionCallInfo fcinfo, XLogRecPtr start_lsn,
+			XLogRecPtr end_lsn, void *params)
+{
+#define PG_GET_WAL_STATS_COLS 9
+	XLogRecPtr	first_record;
+	XLogReaderState *xlogreader;
+	XLogStats stats;
+	ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+	Datum	values[PG_GET_WAL_STATS_COLS];
+	bool	nulls[PG_GET_WAL_STATS_COLS];
+
+	SetSingleFuncCall(fcinfo, 0);
+
+	xlogreader = InitXLogReaderState(start_lsn, &first_record);
+
+	MemSet(&stats, 0, sizeof(stats));
+
+	for (;;)
+	{
+		(void) ReadNextXLogRecord(xlogreader, first_record);
+
+		/*
+		 * Let's not show the record info if it is spanning more than the
+		 * end_lsn. EndRecPtr is "end+1" of the last read record, hence
+		 * use "end" here.
+		 */
+		if ((xlogreader->EndRecPtr - 1) <= end_lsn)
+			XLogRecStoreStats(&stats, xlogreader);
+
+		/* Exit loop if read up to end_lsn. */
+		if (xlogreader->EndRecPtr >= end_lsn)
+			break;
+
+		CHECK_FOR_INTERRUPTS();
+	}
+
+	XLogReaderFree(xlogreader);
+
+	MemSet(values, 0, sizeof(values));
+	MemSet(nulls, 0, sizeof(nulls));
+
+	GetXLogSummaryStats(&stats, rsinfo, values, nulls,
+						PG_GET_WAL_STATS_COLS,
+						((GetWalStatsParams *)params)->stats_per_record);
+
+#undef PG_GET_WAL_STATS_COLS
+}
+
+/*
+ * Get stats of all WAL records between start LSN and end LSN.
+ *
+ * This function emits an error if a future start or end WAL LSN i.e. WAL LSN
+ * the database system doesn't know about is specified.
+ */
+Datum
+pg_get_wal_stats(PG_FUNCTION_ARGS)
+{
+	GetWALDetailsGuts(fcinfo, false, GetWalStats);
+
+	PG_RETURN_VOID();
+}
+
+/*
+ * Get stats of all WAL records from start LSN till end of WAL.
+ *
+ * This function emits an error if a future start i.e. WAL LSN the database
+ * system doesn't know about is specified.
+ */
+Datum
+pg_get_wal_stats_till_end_of_wal(PG_FUNCTION_ARGS)
+{
+	GetWALDetailsGuts(fcinfo, true, GetWalStats);
+
+	PG_RETURN_VOID();
+}
diff --git a/contrib/pg_walinspect/pg_walinspect.control b/contrib/pg_walinspect/pg_walinspect.control
new file mode 100644
index 0000000000..017e56a2bb
--- /dev/null
+++ b/contrib/pg_walinspect/pg_walinspect.control
@@ -0,0 +1,5 @@
+# pg_walinspect extension
+comment = 'functions to inspect contents of PostgreSQL Write-Ahead Log'
+default_version = '1.0'
+module_pathname = '$libdir/pg_walinspect'
+relocatable = true
diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index e437c42992..585c94c488 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.
  *
@@ -1447,6 +1440,12 @@ err:
 	return InvalidXLogRecPtr;
 }
 
+#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.
+ */
 #endif							/* FRONTEND */
 
 /*
diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c
index a4dedc58b7..50159fd4cc 100644
--- a/src/backend/access/transam/xlogutils.c
+++ b/src/backend/access/transam/xlogutils.c
@@ -79,6 +79,10 @@ 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
@@ -851,6 +855,31 @@ wal_segment_close(XLogReaderState *state)
 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;
@@ -906,6 +935,10 @@ 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);
 		}
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 61f06e828f..9dd9f05204 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -27,6 +27,11 @@
 #include "getopt_long.h"
 #include "rmgrdesc.h"
 
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_walinspect contrib module as well.
+ */
+
 static const char *progname;
 
 static int	WalSegSz;
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 09f6464331..3e644372f9 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -31,7 +31,7 @@ extern XLogRecPtr XactLastRecEnd;
 extern PGDLLIMPORT XLogRecPtr XactLastCommitEnd;
 
 /* these variables are GUC parameters related to XLOG */
-extern int	wal_segment_size;
+extern PGDLLIMPORT int	wal_segment_size;
 extern int	min_wal_size_mb;
 extern int	max_wal_size_mb;
 extern int	wal_keep_size_mb;
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index d7c35c37c4..2985c75361 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -319,7 +319,7 @@ typedef struct RmgrData
 							  struct XLogRecordBuffer *buf);
 } RmgrData;
 
-extern const RmgrData RmgrTable[];
+extern PGDLLIMPORT const RmgrData RmgrTable[];
 
 /*
  * Exported to support xlog switching from checkpointer
diff --git a/src/include/access/xlogreader.h b/src/include/access/xlogreader.h
index f4388cc9be..b4c7d93787 100644
--- a/src/include/access/xlogreader.h
+++ b/src/include/access/xlogreader.h
@@ -340,9 +340,7 @@ extern void XLogReaderSetDecodeBuffer(XLogReaderState *state,
 
 /* Position the XLogReader to given record */
 extern void XLogBeginRead(XLogReaderState *state, XLogRecPtr RecPtr);
-#ifdef FRONTEND
 extern XLogRecPtr XLogFindNextRecord(XLogReaderState *state, XLogRecPtr RecPtr);
-#endif							/* FRONTEND */
 
 /* Return values from XLogPageReadCB. */
 typedef enum XLogPageReadResult
diff --git a/src/include/access/xlogutils.h b/src/include/access/xlogutils.h
index 64708949db..22c2299d68 100644
--- a/src/include/access/xlogutils.h
+++ b/src/include/access/xlogutils.h
@@ -92,6 +92,10 @@ extern void FreeFakeRelcacheEntry(Relation fakerel);
 extern int	read_local_xlog_page(XLogReaderState *state,
 								 XLogRecPtr targetPagePtr, int reqLen,
 								 XLogRecPtr targetRecPtr, char *cur_page);
+extern int	read_local_xlog_page_no_wait(XLogReaderState *state,
+										 XLogRecPtr targetPagePtr, int reqLen,
+										 XLogRecPtr targetRecPtr,
+										 char *cur_page);
 extern void wal_segment_open(XLogReaderState *state,
 							 XLogSegNo nextSegNo,
 							 TimeLineID *tli_p);
-- 
2.25.1