v35-0003-Refactor-some-end-of-recovery-code-out-of-Startu.patch

From b5e6bd6fd572b23a087adfcc448e180e91f6d4ce Mon Sep 17 00:00:00 2001
From: Amul Sul <amul.sul@enterprisedb.com>
Date: Mon, 20 Sep 2021 07:40:07 -0400
Subject: [PATCH v35 3/5] Refactor some end-of-recovery code out of
 StartupXLOG().

Moved the code that performs whether to write a checkpoint or an
end-of-recovery record into PerformRecoveryXlogAction().

Also create a new function CleanupAfterArchiveRecovery() to
perform a few tasks that we want to do after we've actually exited
archive recovery but before we start accepting new WAL writes.
This is straightforward code movement to make StartupXLOG() a
little bit shorter and a little bit easier to understand.

Robert Haas, with modifications by Amul Sul.
---
 src/backend/access/transam/xlog.c | 285 ++++++++++++++++--------------
 1 file changed, 154 insertions(+), 131 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index c9d5bf9a72c..12f7e080d3e 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -892,6 +892,7 @@ static MemoryContext walDebugCxt = NULL;
 static void readRecoverySignalFile(void);
 static void validateRecoveryParameters(void);
 static void exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog);
+static void CleanupAfterArchiveRecovery(void);
 static bool recoveryStopsBefore(XLogReaderState *record);
 static bool recoveryStopsAfter(XLogReaderState *record);
 static char *getRecoveryStopReason(void);
@@ -937,6 +938,7 @@ static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force);
 static XLogRecord *ReadRecord(XLogReaderState *xlogreader,
 							  int emode, bool fetching_ckpt);
 static void CheckRecoveryConsistency(void);
+static bool PerformRecoveryXLogAction(void);
 static XLogRecord *ReadCheckpointRecord(XLogReaderState *xlogreader,
 										XLogRecPtr RecPtr, int whichChkpt, bool report);
 static bool rescanLatestTimeLine(void);
@@ -5713,6 +5715,101 @@ exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog)
 			(errmsg("archive recovery complete")));
 }
 
+/*
+ * Perform cleanup actions at the conclusion of archive recovery.
+ */
+static void
+CleanupAfterArchiveRecovery(void)
+{
+	XLogRecPtr	EndOfLog;
+
+	/*
+	 * Execute the recovery_end_command, if any.
+	 */
+	if (recoveryEndCommand && strcmp(recoveryEndCommand, "") != 0)
+		ExecuteRecoveryCommand(recoveryEndCommand,
+							   "recovery_end_command",
+							   true);
+
+	/*
+	 * We switched to a new timeline. Clean up segments on the old timeline.
+	 *
+	 * If there are any higher-numbered segments on the old timeline, remove
+	 * them. They might contain valid WAL, but they might also be pre-allocated
+	 * files containing garbage. In any case, they are not part of the new
+	 * timeline's history so we don't need them.
+	 */
+	(void) GetLastSegSwitchData(&EndOfLog);
+	RemoveNonParentXlogFiles(EndOfLog, ThisTimeLineID);
+
+	/*
+	 * If the switch happened in the middle of a segment, what to do with the
+	 * last, partial segment on the old timeline? If we don't archive it, and
+	 * the server that created the WAL never archives it either (e.g. because it
+	 * was hit by a meteor), it will never make it to the archive. That's OK
+	 * from our point of view, because the new segment that we created with the
+	 * new TLI contains all the WAL from the old timeline up to the switch
+	 * point. But if you later try to do PITR to the "missing" WAL on the old
+	 * timeline, recovery won't find it in the archive. It's physically present
+	 * in the new file with new TLI, but recovery won't look there when it's
+	 * recovering to the older timeline. On the other hand, if we archive the
+	 * partial segment, and the original server on that timeline is still
+	 * running and archives the completed version of the same segment later, it
+	 * will fail. (We used to do that in 9.4 and below, and it caused such
+	 * problems).
+	 *
+	 * As a compromise, we rename the last segment with the .partial suffix, and
+	 * archive it. Archive recovery will never try to read .partial segments, so
+	 * they will normally go unused. But in the odd PITR case, the administrator
+	 * can copy them manually to the pg_wal directory (removing the suffix).
+	 * They can be useful in debugging, too.
+	 *
+	 * If a .done or .ready file already exists for the old timeline, however,
+	 * we had already determined that the segment is complete, so we can let it
+	 * be archived normally. (In particular, if it was restored from the archive
+	 * to begin with, it's expected to have a .done file).
+	 */
+	if (XLogSegmentOffset(EndOfLog, wal_segment_size) != 0 &&
+		XLogArchivingActive())
+	{
+		char		origfname[MAXFNAMELEN];
+		XLogSegNo	endLogSegNo;
+		TimeLineID	EndOfLogTLI = XLogCtl->replayEndTLI;
+
+		XLByteToPrevSeg(EndOfLog, endLogSegNo, wal_segment_size);
+		XLogFileName(origfname, EndOfLogTLI, endLogSegNo, wal_segment_size);
+
+		if (!XLogArchiveIsReadyOrDone(origfname))
+		{
+			char		origpath[MAXPGPATH];
+			char		partialfname[MAXFNAMELEN];
+			char		partialpath[MAXPGPATH];
+
+			XLogFilePath(origpath, EndOfLogTLI, endLogSegNo, wal_segment_size);
+			snprintf(partialfname, MAXFNAMELEN, "%s.partial", origfname);
+			snprintf(partialpath, MAXPGPATH, "%s.partial", origpath);
+
+			/*
+			 * Make sure there's no .done or .ready file for the .partial
+			 * file.
+			 */
+			XLogArchiveCleanup(partialfname);
+
+			durable_rename(origpath, partialpath, ERROR);
+			XLogArchiveNotify(partialfname);
+		}
+	}
+
+	/*
+	 * Done with archive recovery request, clear the shared memory state which
+	 * no longer needed.
+	 */
+	SpinLockAcquire(&XLogCtl->info_lck);
+	XLogCtl->SharedArchiveRecoveryRequested = false;
+	ArchiveRecoveryRequested = ARCHIVE_RECOVERY_REQUEST_UNKOWN;
+	SpinLockRelease(&XLogCtl->info_lck);
+}
+
 /*
  * Extract timestamp from WAL record.
  *
@@ -7907,139 +8004,11 @@ StartupXLOG(void)
 	 * shut down cleanly, which been through recovery.
 	 */
 	if (ControlFile->state != DB_SHUTDOWNED)
-	{
-		/*
-		 * Perform a checkpoint to update all our recovery activity to disk.
-		 *
-		 * Note that we write a shutdown checkpoint rather than an on-line
-		 * one. This is not particularly critical, but since we may be
-		 * assigning a new TLI, using a shutdown checkpoint allows us to have
-		 * the rule that TLI only changes in shutdown checkpoints, which
-		 * allows some extra error checking in xlog_redo.
-		 *
-		 * In promotion, only create a lightweight end-of-recovery record
-		 * instead of a full checkpoint. A checkpoint is requested later,
-		 * after we're fully out of recovery mode and already accepting
-		 * queries.
-		 */
-		if (ArchiveRecoveryIsRequested() && IsUnderPostmaster &&
-			PromoteIsTriggered())
-		{
-			promoted = true;
-
-			/*
-			 * Insert a special WAL record to mark the end of recovery, since
-			 * we aren't doing a checkpoint. That means that the checkpointer
-			 * process may likely be in the middle of a time-smoothed
-			 * restartpoint and could continue to be for minutes after this.
-			 * That sounds strange, but the effect is roughly the same and it
-			 * would be stranger to try to come out of the restartpoint and
-			 * then checkpoint. We request a checkpoint later anyway, just for
-			 * safety.
-			 */
-			CreateEndOfRecoveryRecord();
-		}
-		else
-		{
-			RequestCheckpoint(CHECKPOINT_END_OF_RECOVERY |
-							  CHECKPOINT_IMMEDIATE |
-							  CHECKPOINT_WAIT);
-		}
-	}
+		promoted = PerformRecoveryXLogAction();
 
+	/* If this is archive recovery, perform post-recovery cleanup actions. */
 	if (ArchiveRecoveryIsRequested())
-	{
-		XLogRecPtr	EndOfLog;
-
-		/*
-		 * And finally, execute the recovery_end_command, if any.
-		 */
-		if (recoveryEndCommand && strcmp(recoveryEndCommand, "") != 0)
-			ExecuteRecoveryCommand(recoveryEndCommand,
-								   "recovery_end_command",
-								   true);
-
-		/*
-		 * We switched to a new timeline. Clean up segments on the old
-		 * timeline.
-		 *
-		 * If there are any higher-numbered segments on the old timeline,
-		 * remove them. They might contain valid WAL, but they might also be
-		 * pre-allocated files containing garbage. In any case, they are not
-		 * part of the new timeline's history so we don't need them.
-		 */
-		(void) GetLastSegSwitchData(&EndOfLog);
-		RemoveNonParentXlogFiles(EndOfLog, ThisTimeLineID);
-
-		/*
-		 * If the switch happened in the middle of a segment, what to do with
-		 * the last, partial segment on the old timeline? If we don't archive
-		 * it, and the server that created the WAL never archives it either
-		 * (e.g. because it was hit by a meteor), it will never make it to the
-		 * archive. That's OK from our point of view, because the new segment
-		 * that we created with the new TLI contains all the WAL from the old
-		 * timeline up to the switch point. But if you later try to do PITR to
-		 * the "missing" WAL on the old timeline, recovery won't find it in
-		 * the archive. It's physically present in the new file with new TLI,
-		 * but recovery won't look there when it's recovering to the older
-		 * timeline. On the other hand, if we archive the partial segment, and
-		 * the original server on that timeline is still running and archives
-		 * the completed version of the same segment later, it will fail. (We
-		 * used to do that in 9.4 and below, and it caused such problems).
-		 *
-		 * As a compromise, we rename the last segment with the .partial
-		 * suffix, and archive it. Archive recovery will never try to read
-		 * .partial segments, so they will normally go unused. But in the odd
-		 * PITR case, the administrator can copy them manually to the pg_wal
-		 * directory (removing the suffix). They can be useful in debugging,
-		 * too.
-		 *
-		 * If a .done or .ready file already exists for the old timeline,
-		 * however, we had already determined that the segment is complete, so
-		 * we can let it be archived normally. (In particular, if it was
-		 * restored from the archive to begin with, it's expected to have a
-		 * .done file).
-		 */
-		if (XLogSegmentOffset(EndOfLog, wal_segment_size) != 0 &&
-			XLogArchivingActive())
-		{
-			char		origfname[MAXFNAMELEN];
-			XLogSegNo	endLogSegNo;
-			TimeLineID	EndOfLogTLI = XLogCtl->replayEndTLI;
-
-			XLByteToPrevSeg(EndOfLog, endLogSegNo, wal_segment_size);
-			XLogFileName(origfname, EndOfLogTLI, endLogSegNo, wal_segment_size);
-
-			if (!XLogArchiveIsReadyOrDone(origfname))
-			{
-				char		origpath[MAXPGPATH];
-				char		partialfname[MAXFNAMELEN];
-				char		partialpath[MAXPGPATH];
-
-				XLogFilePath(origpath, EndOfLogTLI, endLogSegNo, wal_segment_size);
-				snprintf(partialfname, MAXFNAMELEN, "%s.partial", origfname);
-				snprintf(partialpath, MAXPGPATH, "%s.partial", origpath);
-
-				/*
-				 * Make sure there's no .done or .ready file for the .partial
-				 * file.
-				 */
-				XLogArchiveCleanup(partialfname);
-
-				durable_rename(origpath, partialpath, ERROR);
-				XLogArchiveNotify(partialfname);
-			}
-		}
-
-		/*
-		 * Done with archive recovery request, clear the shared memory state
-		 * which no longer needed.
-		 */
-		SpinLockAcquire(&XLogCtl->info_lck);
-		XLogCtl->SharedArchiveRecoveryRequested = false;
-		ArchiveRecoveryRequested = ARCHIVE_RECOVERY_REQUEST_UNKOWN;
-		SpinLockRelease(&XLogCtl->info_lck);
-	}
+		CleanupAfterArchiveRecovery();
 
 	/*
 	 * Preallocate additional log files, if wanted.
@@ -8243,6 +8212,60 @@ CheckRecoveryConsistency(void)
 	}
 }
 
+/*
+ * Perform whatever XLOG actions are necessary at end of REDO.
+ *
+ * The goal here is to make sure that we'll be able to recover properly if
+ * we crash again. If we choose to write a checkpoint, we'll write a shutdown
+ * checkpoint rather than an on-line one. This is not particularly critical,
+ * but since we may be assigning a new TLI, using a shutdown checkpoint allows
+ * us to have the rule that TLI only changes in shutdown checkpoints, which
+ * allows some extra error checking in xlog_redo.
+ */
+static bool
+PerformRecoveryXLogAction(void)
+{
+	bool		promoted = false;
+
+	/*
+	 * Perform a checkpoint to update all our recovery activity to disk.
+	 *
+	 * Note that we write a shutdown checkpoint rather than an on-line one. This
+	 * is not particularly critical, but since we may be assigning a new TLI,
+	 * using a shutdown checkpoint allows us to have the rule that TLI only
+	 * changes in shutdown checkpoints, which allows some extra error checking
+	 * in xlog_redo.
+	 *
+	 * In promotion, only create a lightweight end-of-recovery record instead of
+	 * a full checkpoint. A checkpoint is requested later, after we're fully out
+	 * of recovery mode and already accepting queries.
+	 */
+	if (ArchiveRecoveryIsRequested() && IsUnderPostmaster &&
+		PromoteIsTriggered())
+	{
+		promoted = true;
+
+		/*
+		 * Insert a special WAL record to mark the end of recovery, since we
+		 * aren't doing a checkpoint. That means that the checkpointer process
+		 * may likely be in the middle of a time-smoothed restartpoint and could
+		 * continue to be for minutes after this.  That sounds strange, but the
+		 * effect is roughly the same and it would be stranger to try to come
+		 * out of the restartpoint and then checkpoint. We request a checkpoint
+		 * later anyway, just for safety.
+		 */
+		CreateEndOfRecoveryRecord();
+	}
+	else
+	{
+		RequestCheckpoint(CHECKPOINT_END_OF_RECOVERY |
+						  CHECKPOINT_IMMEDIATE |
+						  CHECKPOINT_WAIT);
+	}
+
+	return promoted;
+}
+
 /*
  * Is the system still in recovery?
  *
-- 
2.18.0