agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v53 3/7] Make archiver process an auxiliary process
135+ messages / 3 participants
[nested] [flat]

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread

* [PATCH v9] Be more picky with WAL segment deletion in pg_rewind
@ 2023-08-06 14:56 Alexander Kukushkin <[email protected]>
  0 siblings, 0 replies; 135+ messages in thread

From: Alexander Kukushkin @ 2023-08-06 14:56 UTC (permalink / raw)

Make pg_rewind to be a bit wiser in terms of creating filemap:
preserve on the target all WAL segments that contain records between the
last common checkpoint and the point of divergence.

Co-authored-by: Polina Bungina <[email protected]>
---
 src/bin/pg_rewind/filemap.c                   | 62 +++++++++++++++++-
 src/bin/pg_rewind/filemap.h                   |  3 +
 src/bin/pg_rewind/meson.build                 |  1 +
 src/bin/pg_rewind/parsexlog.c                 | 24 +++++++
 src/bin/pg_rewind/pg_rewind.c                 |  3 +
 src/bin/pg_rewind/t/010_keep_recycled_wals.pl | 65 +++++++++++++++++++
 6 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 src/bin/pg_rewind/t/010_keep_recycled_wals.pl

diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 4458324c9d8..b357c28338a 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -63,6 +63,28 @@ static file_entry_t *lookup_filehash_entry(const char *path);
 static int	final_filemap_cmp(const void *a, const void *b);
 static bool check_file_excluded(const char *path, bool is_source);
 
+typedef struct skipwal_t
+{
+	const char *path;
+	uint32		status;
+}			skipwal_t;
+
+#define SH_PREFIX		keepwalhash
+#define SH_ELEMENT_TYPE	skipwal_t
+#define SH_KEY_TYPE		const char *
+#define	SH_KEY			path
+#define SH_HASH_KEY(tb, key)	hash_string(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define	SH_SCOPE		static inline
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static keepwalhash_hash * keepwalhash = NULL;
+
+static bool keepwalhash_entry_exists(const char *path);
+
 /*
  * Definition of one element part of an exclusion list, used to exclude
  * contents when rewinding.  "name" is the name of the file or path to
@@ -206,6 +228,35 @@ lookup_filehash_entry(const char *path)
 	return filehash_lookup(filehash, path);
 }
 
+/* Initialize a hash table to store WAL file names that must be kept */
+void
+keepwalhash_init(void)
+{
+	keepwalhash = keepwalhash_create(FILEHASH_INITIAL_SIZE, NULL);
+}
+
+/* Prevent a given file deletion during rewind */
+void
+insert_keepwalhash_entry(const char *path)
+{
+	skipwal_t  *entry;
+	bool		found;
+
+	/* Should only be called with keepwalhash initialized */
+	Assert(keepwalhash);
+
+	entry = keepwalhash_insert(keepwalhash, path, &found);
+
+	if (!found)
+		entry->path = pg_strdup(path);
+}
+
+static bool
+keepwalhash_entry_exists(const char *path)
+{
+	return keepwalhash_lookup(keepwalhash, path) != NULL;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -685,7 +736,16 @@ decide_file_action(file_entry_t *entry)
 	}
 	else if (entry->target_exists && !entry->source_exists)
 	{
-		/* File exists in target, but not source. Remove it. */
+		/* File exists in target, but not source. */
+
+		if (keepwalhash_entry_exists(path))
+		{
+			/* This is a WAL file that should be kept. */
+			pg_log_debug("Not removing %s because it is required for recovery", path);
+			return FILE_ACTION_NONE;
+		}
+
+		/* Otherwise remove an unexpected file. */
 		return FILE_ACTION_REMOVE;
 	}
 	else if (!entry->target_exists && !entry->source_exists)
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 007e0f17cf4..0cb6fcae00c 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -110,4 +110,7 @@ extern filemap_t *decide_file_actions(void);
 extern void calculate_totals(filemap_t *filemap);
 extern void print_filemap(filemap_t *filemap);
 
+extern void keepwalhash_init(void);
+extern void insert_keepwalhash_entry(const char *path);
+
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/meson.build b/src/bin/pg_rewind/meson.build
index e0f88bde221..200ebf84eb9 100644
--- a/src/bin/pg_rewind/meson.build
+++ b/src/bin/pg_rewind/meson.build
@@ -43,6 +43,7 @@ tests += {
       't/007_standby_source.pl',
       't/008_min_recovery_point.pl',
       't/009_growing_files.pl',
+      't/010_keep_recycled_wals.pl',
     ],
   },
 }
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 22f7351fdcd..7329c06d8fa 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -176,6 +176,10 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 	char	   *errormsg;
 	XLogPageReadPrivate private;
 
+	/* Track WAL segments opened while searching a checkpoint */
+	XLogSegNo	segno = 0;
+	TimeLineID	tli = 0;
+
 	/*
 	 * The given fork pointer points to the end of the last common record,
 	 * which is not necessarily the beginning of the next record, if the
@@ -217,6 +221,26 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex,
 						 LSN_FORMAT_ARGS(searchptr));
 		}
 
+		/* We are trying to detect if the new WAL file was opened */
+		if (xlogreader->seg.ws_tli != tli || xlogreader->seg.ws_segno != segno)
+		{
+			char		xlogfname[MAXFNAMELEN];
+
+			tli = xlogreader->seg.ws_tli;
+			segno = xlogreader->seg.ws_segno;
+
+			snprintf(xlogfname, MAXPGPATH, XLOGDIR "/");
+			XLogFileName(xlogfname + strlen(xlogfname),
+						 xlogreader->seg.ws_tli,
+						 xlogreader->seg.ws_segno, WalSegSz);
+
+			/*
+			 * Make sure pg_rewind doesn't remove this file, because it is
+			 * required for postgres to start after rewind.
+			 */
+			insert_keepwalhash_entry(xlogfname);
+		}
+
 		/*
 		 * Check if it is a checkpoint record. This checkpoint record needs to
 		 * be the latest checkpoint before WAL forked and not the checkpoint
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 0841ab4135b..48c11417b23 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -455,6 +455,9 @@ main(int argc, char **argv)
 		exit(0);
 	}
 
+	/* Hash to memorize WAL files that should be kept */
+	keepwalhash_init();
+
 	findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex,
 					   &chkptrec, &chkpttli, &chkptredo, restore_command);
 	pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u",
diff --git a/src/bin/pg_rewind/t/010_keep_recycled_wals.pl b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
new file mode 100644
index 00000000000..65caaf2faa2
--- /dev/null
+++ b/src/bin/pg_rewind/t/010_keep_recycled_wals.pl
@@ -0,0 +1,65 @@
+
+# Copyright (c) 2021-2024, PostgreSQL Global Development Group
+
+#
+# Test situation where a target data directory contains
+# WAL files that were already recycled by the new primary.
+#
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+use FindBin;
+use lib $FindBin::RealBin;
+
+use RewindTest;
+
+RewindTest::setup_cluster();
+$node_primary->enable_archiving();
+RewindTest::start_primary();
+
+RewindTest::create_standby();
+$node_standby->enable_restoring($node_primary, 0);
+$node_standby->reload();
+
+RewindTest::primary_psql("CHECKPOINT");  # last common checkpoint
+
+# We use "perl -e 'exit(1)'" as an alternative to "false", because the last one
+# might not be available on Windows, but we want to run tests cross-platform.
+my $false = "$^X -e 'exit(1)'";
+$node_primary->append_conf(
+	'postgresql.conf', qq(
+archive_command = '$false'
+));
+$node_primary->reload();
+
+# advance WAL on the primary; WAL segment will never make it to the archive
+RewindTest::primary_psql("CREATE TABLE t(a int)");
+RewindTest::primary_psql("INSERT INTO t VALUES(0)");
+RewindTest::primary_psql("SELECT pg_switch_wal()");
+
+RewindTest::promote_standby;
+
+# new primary loses diverging WAL segment
+RewindTest::standby_psql("INSERT INTO t values(0)");
+RewindTest::standby_psql("SELECT pg_switch_wal()");
+
+$node_standby->stop();
+$node_primary->stop();
+
+my ($stdout, $stderr) = run_command(
+	[
+		'pg_rewind', '--debug',
+		'--source-pgdata', $node_standby->data_dir,
+		'--target-pgdata', $node_primary->data_dir,
+		'--no-sync',
+	]);
+
+like(
+	$stderr,
+	qr/Not removing pg_wal.* because it is required for recovery/,
+	"some WAL files were skipped");
+
+done_testing();
-- 
2.45.2


----Next_Part(Fri_Jul_12_16_24_06_2024_549)----





^ permalink  raw  reply  [nested|flat] 135+ messages in thread