v4-0001-Emit-record-LSN-in-WAL-read-and-validate-error-me.patch

application/x-patch

Filename: v4-0001-Emit-record-LSN-in-WAL-read-and-validate-error-me.patch
Type: application/x-patch
Part: 0
Message: Re: Add LSN along with offset to error messages reported for WAL file read/write/validate header failures

Patch

Format: format-patch
Series: patch v4-0001
Subject: Emit record LSN in WAL read and validate error messages
File+
src/backend/access/transam/xlogreader.c 10 5
src/backend/access/transam/xlogrecovery.c 8 5
From 452f6adc4617230f8843a9339331170cb6f85723 Mon Sep 17 00:00:00 2001
From: Bharath Rupireddy <bharath.rupireddyforpostgres@gmail.com>
Date: Sat, 3 Dec 2022 03:13:57 +0000
Subject: [PATCH v4] Emit record LSN in WAL read and validate error messages

The error messages reported during any failures in WAL record read
or validation currently contains offset within the WAL file which
is a bit hard to decode it to WAL LSN while debugging. Reporting
the WAL record LSN at which the WAL read or validation failure
occurrs saves time and makes life easier here.

Author: Bharath Rupireddy
Reviewed-by: Maxim Orlov, Michael Paquier
Reviewed-by: Kyotaro Horiguchi
Discussion: https://www.postgresql.org/message-id/CALj2ACWV=FCddsxcGbVOA=cvPyMr75YCFbSQT6g4KDj=gcJK4g@mail.gmail.com
---
 src/backend/access/transam/xlogreader.c   | 15 ++++++++++-----
 src/backend/access/transam/xlogrecovery.c | 13 ++++++++-----
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index 93f667b254..a38a80e049 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -1226,9 +1226,10 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 		XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize);
 
 		report_invalid_record(state,
-							  "invalid magic number %04X in WAL segment %s, offset %u",
+							  "invalid magic number %04X in WAL segment %s, LSN %X/%X, offset %u",
 							  hdr->xlp_magic,
 							  fname,
+							  LSN_FORMAT_ARGS(recptr),
 							  offset);
 		return false;
 	}
@@ -1240,9 +1241,10 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 		XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize);
 
 		report_invalid_record(state,
-							  "invalid info bits %04X in WAL segment %s, offset %u",
+							  "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u",
 							  hdr->xlp_info,
 							  fname,
+							  LSN_FORMAT_ARGS(recptr),
 							  offset);
 		return false;
 	}
@@ -1281,9 +1283,10 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 
 		/* hmm, first page of file doesn't have a long header? */
 		report_invalid_record(state,
-							  "invalid info bits %04X in WAL segment %s, offset %u",
+							  "invalid info bits %04X in WAL segment %s, LSN %X/%X, offset %u",
 							  hdr->xlp_info,
 							  fname,
+							  LSN_FORMAT_ARGS(recptr),
 							  offset);
 		return false;
 	}
@@ -1300,9 +1303,10 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 		XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize);
 
 		report_invalid_record(state,
-							  "unexpected pageaddr %X/%X in WAL segment %s, offset %u",
+							  "unexpected pageaddr %X/%X in WAL segment %s, LSN %X/%X, offset %u",
 							  LSN_FORMAT_ARGS(hdr->xlp_pageaddr),
 							  fname,
+							  LSN_FORMAT_ARGS(recptr),
 							  offset);
 		return false;
 	}
@@ -1325,10 +1329,11 @@ XLogReaderValidatePageHeader(XLogReaderState *state, XLogRecPtr recptr,
 			XLogFileName(fname, state->seg.ws_tli, segno, state->segcxt.ws_segsize);
 
 			report_invalid_record(state,
-								  "out-of-sequence timeline ID %u (after %u) in WAL segment %s, offset %u",
+								  "out-of-sequence timeline ID %u (after %u) in WAL segment %s, LSN %X/%X, offset %u",
 								  hdr->xlp_tli,
 								  state->latestPageTLI,
 								  fname,
+								  LSN_FORMAT_ARGS(recptr),
 								  offset);
 			return false;
 		}
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index 41ffc57da9..97b882564f 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -3075,9 +3075,10 @@ ReadRecord(XLogPrefetcher *xlogprefetcher, int emode,
 			XLogFileName(fname, xlogreader->seg.ws_tli, segno,
 						 wal_segment_size);
 			ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr),
-					(errmsg("unexpected timeline ID %u in WAL segment %s, offset %u",
+					(errmsg("unexpected timeline ID %u in WAL segment %s, LSN %X/%X, offset %u",
 							xlogreader->latestPageTLI,
 							fname,
+							LSN_FORMAT_ARGS(xlogreader->latestPagePtr),
 							offset)));
 			record = NULL;
 		}
@@ -3280,14 +3281,16 @@ retry:
 			errno = save_errno;
 			ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen),
 					(errcode_for_file_access(),
-					 errmsg("could not read from WAL segment %s, offset %u: %m",
-							fname, readOff)));
+					 errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: %m",
+							fname, LSN_FORMAT_ARGS(targetPagePtr),
+							readOff)));
 		}
 		else
 			ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen),
 					(errcode(ERRCODE_DATA_CORRUPTED),
-					 errmsg("could not read from WAL segment %s, offset %u: read %d of %zu",
-							fname, readOff, r, (Size) XLOG_BLCKSZ)));
+					 errmsg("could not read from WAL segment %s, LSN %X/%X, offset %u: read %d of %zu",
+							fname, LSN_FORMAT_ARGS(targetPagePtr),
+							readOff, r, (Size) XLOG_BLCKSZ)));
 		goto next_record_is_invalid;
 	}
 	pgstat_report_wait_end();
-- 
2.34.1