recovery-archives-v6.patch

diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index f60ed2d36c..2cce871dc9 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -166,6 +166,14 @@ typedef enum WalLevel
 	WAL_LEVEL_LOGICAL
 } WalLevel;
 
+/* Recovery states */
+typedef enum RecoveryState
+{
+	RECOVERY_STATE_CRASH = 0,	/* crash recovery */
+	RECOVERY_STATE_ARCHIVE,		/* archive recovery */
+	RECOVERY_STATE_NONE			/* currently in production */
+} RecoveryState;
+
 extern PGDLLIMPORT int wal_level;
 
 /* Is WAL archiving enabled (always or only while server is running normally)? */
@@ -291,6 +299,7 @@ extern const char *xlog_identify(uint8 info);
 extern void issue_xlog_fsync(int fd, XLogSegNo segno);
 
 extern bool RecoveryInProgress(void);
+extern RecoveryState GetRecoveryState(void);
 extern bool HotStandbyActive(void);
 extern bool HotStandbyActiveInReplay(void);
 extern bool XLogInsertAllowed(void);
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 11e32733c4..a1372b08f6 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -221,8 +221,9 @@ static TimeLineID receiveTLI = 0;
 static bool lastFullPageWrites;
 
 /*
- * Local copy of SharedRecoveryInProgress variable. True actually means "not
- * known, need to check the shared state".
+ * Local copy of the state tracked by SharedRecoveryState in shared memory,
+ * It is false if SharedRecoveryState is RECOVERY_STATE_NONE.  True actually
+ * means "not known, need to check the shared state".
  */
 static bool LocalRecoveryInProgress = true;
 
@@ -653,10 +654,10 @@ typedef struct XLogCtlData
 	TimeLineID	PrevTimeLineID;
 
 	/*
-	 * SharedRecoveryInProgress indicates if we're still in crash or archive
+	 * SharedRecoveryState indicates if we're either in crash or archive
 	 * recovery.  Protected by info_lck.
 	 */
-	bool		SharedRecoveryInProgress;
+	RecoveryState	SharedRecoveryState;
 
 	/*
 	 * SharedHotStandbyActive indicates if we allow hot standby queries to be
@@ -4434,6 +4435,16 @@ ReadRecord(XLogReaderState *xlogreader, int emode,
 				updateMinRecoveryPoint = true;
 
 				UpdateControlFile();
+
+				/*
+				 * We update SharedRecoveryState while holding the lock on
+				 * ControlFileLock so both states are consistent in shared
+				 * memory.
+				 */
+				SpinLockAcquire(&XLogCtl->info_lck);
+				XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;
+				SpinLockRelease(&XLogCtl->info_lck);
+
 				LWLockRelease(ControlFileLock);
 
 				CheckRecoveryConsistency();
@@ -5166,10 +5177,10 @@ XLOGShmemInit(void)
 	 * in additional info.)
 	 */
 	XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
-	XLogCtl->SharedRecoveryInProgress = true;
 	XLogCtl->SharedHotStandbyActive = false;
 	XLogCtl->SharedPromoteIsTriggered = false;
 	XLogCtl->WalWriterSleeping = false;
+	XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
 
 	SpinLockInit(&XLogCtl->Insert.insertpos_lck);
 	SpinLockInit(&XLogCtl->info_lck);
@@ -7911,7 +7922,7 @@ StartupXLOG(void)
 	ControlFile->time = (pg_time_t) time(NULL);
 
 	SpinLockAcquire(&XLogCtl->info_lck);
-	XLogCtl->SharedRecoveryInProgress = false;
+	XLogCtl->SharedRecoveryState = RECOVERY_STATE_NONE;
 	SpinLockRelease(&XLogCtl->info_lck);
 
 	UpdateControlFile();
@@ -8057,7 +8068,7 @@ RecoveryInProgress(void)
 		 */
 		volatile XLogCtlData *xlogctl = XLogCtl;
 
-		LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;
+		LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_NONE);
 
 		/*
 		 * Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -8069,8 +8080,8 @@ RecoveryInProgress(void)
 		{
 			/*
 			 * If we just exited recovery, make sure we read TimeLineID and
-			 * RedoRecPtr after SharedRecoveryInProgress (for machines with
-			 * weak memory ordering).
+			 * RedoRecPtr after SharedRecoveryState (for machines with weak
+			 * memory ordering).
 			 */
 			pg_memory_barrier();
 			InitXLOGAccess();
@@ -8086,6 +8097,24 @@ RecoveryInProgress(void)
 	}
 }
 
+/*
+ * Returns current recovery state from shared memory.
+ *
+ * This returned state is accurate after StartupXLOG() finished.  See
+ * details about the possible values of RecoveryState in xlog.h.
+ */
+RecoveryState
+GetRecoveryState(void)
+{
+	RecoveryState	retval;
+
+	SpinLockAcquire(&XLogCtl->info_lck);
+	retval = XLogCtl->SharedRecoveryState;
+	SpinLockRelease(&XLogCtl->info_lck);
+
+	return retval;
+}
+
 /*
  * Is HotStandby active yet? This is only important in special backends
  * since normal backends won't ever be able to connect until this returns
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index d62c12310a..ce0127c3d0 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -572,17 +572,21 @@ XLogArchiveCheckDone(const char *xlog)
 {
 	char		archiveStatusPath[MAXPGPATH];
 	struct stat stat_buf;
-	bool		inRecovery = RecoveryInProgress();
+
+	/* The file is always deletable if archive_mode is "off". */
+	if (!XLogArchivingActive())
+		return true;
+
+	/* On standbys, the file is deletable if archive_mode is not "always". */
+	if (!XLogArchivingAlways() &&
+		GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
+		return true;
 
 	/*
-	 * The file is always deletable if archive_mode is "off".  On standbys
-	 * archiving is disabled if archive_mode is "on", and enabled with
-	 * "always".  On a primary, archiving is enabled if archive_mode is "on"
-	 * or "always".
+	 * At this point of the logic, note that we are either a primary with
+	 * with archive_mode set to "on" or "always", or a standby with
+	 * archive_mode set to "always".
 	 */
-	if (!((XLogArchivingActive() && !inRecovery) ||
-		  (XLogArchivingAlways() && inRecovery)))
-		return true;
 
 	/* First check for .done --- this means archiver is done with it */
 	StatusFilePath(archiveStatusPath, xlog, ".done");
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.pl
new file mode 100644
index 0000000000..a5f4fd821a
--- /dev/null
+++ b/src/test/recovery/t/020_archive_status.pl
@@ -0,0 +1,193 @@
+#
+# Tests relating to WAL archiving and cleanup
+#
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+use Config;
+
+my ($node, $standby1, $standby2);
+my ($node_data, $standby1_data, $standby2_data);
+
+if ($Config{osname} eq 'MSWin32')
+{
+
+	# some Windows Perls at least don't like IPC::Run's start/kill_kill regime.
+	plan skip_all => "Test fails on Windows perl";
+}
+else
+{
+	plan tests => 16;
+}
+
+$node = get_new_node('master');
+$node->init(
+	has_archiving => 1,
+	allows_streaming => 1
+);
+$node->start;
+$node_data = $node->data_dir;
+
+# temporary fail archive_command for futur tests
+$node->safe_psql('postgres', q{
+	ALTER SYSTEM SET archive_command TO 'false';
+	SELECT pg_reload_conf();
+});
+
+$node->safe_psql('postgres', q{
+	CREATE TABLE mine AS SELECT generate_series(1,10) AS x;
+	SELECT pg_switch_wal();
+	CHECKPOINT;
+});
+
+# wait for archive failure
+$node->poll_query_until('postgres',
+	q{SELECT failed_count > 0 FROM pg_stat_archiver},
+	't') or die "Timed out while waiting for archiver to fail";
+
+ok( -f "$node_data/pg_wal/archive_status/000000010000000000000001.ready",
+  "ready file exists for WAL waiting to be archived");
+
+is($node->safe_psql('postgres', q{
+		SELECT archived_count, last_failed_wal
+		FROM pg_stat_archiver
+	}),
+	'0|000000010000000000000001', 'pg_stat_archiver reports archive failure');
+
+# We need to crash the cluster because next test checks the crash
+# recovery step do not removes non-archived WAL.
+$node->stop('immediate');
+
+# Standby recovery tests checks the recovery behavior when restoring a
+# backup taken using eg. a snapshot with no pg_start/stop_backup.
+# In this situation, the recovered standby should enter first crash
+# recovery then switch to regular archive recovery.
+$node->backup_fs_cold('backup');
+
+$node->start;
+
+ok( -f "$node_data/pg_wal/archive_status/000000010000000000000001.ready",
+  "WAL segment still ready to archive after crash recovery on primary");
+
+# Allow WAL archiving again
+$node->safe_psql('postgres', q{
+	ALTER SYSTEM RESET archive_command;
+	SELECT pg_reload_conf();
+});
+
+# wait for archive success
+$node->poll_query_until('postgres',
+	q{SELECT archived_count FROM pg_stat_archiver},
+	'1')  or die "Timed out while waiting for archiver to success";
+
+ok( ! -f "$node_data/pg_wal/archive_status/000000010000000000000001.ready",
+  "ready file for archived WAL removed");
+
+ok( -f "$node_data/pg_wal/archive_status/000000010000000000000001.done",
+  "done file for archived WAL exists");
+
+is($node->safe_psql('postgres',
+		q{ SELECT last_archived_wal FROM pg_stat_archiver }),
+	'000000010000000000000001',
+	'Archive success reported in pg_stat_archiver');
+
+# create some wal activity and a new checkpoint so futur standby can create
+# a restartpoint.
+# As standby start in crash recovery because of the backup method, they need
+# a clean restartpoint to deal with existing status files.
+$node->safe_psql('postgres', q{
+	INSERT INTO mine SELECT generate_series(10,20) AS x;
+	SELECT pg_switch_wal();
+	CHECKPOINT;
+});
+
+$node->poll_query_until('postgres',
+	q{ SELECT last_archived_wal FROM pg_stat_archiver },
+	'000000010000000000000002')  or die "Timed out while waiting for archiver to succeed";
+
+# tests standby with archive_mode=on
+$standby1 = get_new_node('standby');
+$standby1->init_from_backup($node, 'backup', has_restoring => 1);
+$standby1->append_conf('postgresql.conf', "archive_mode = on");
+$standby1_data = $standby1->data_dir;
+$standby1->start;
+$standby1->safe_psql('postgres', q{CHECKPOINT});
+
+# recovery with archive_mode=on does not keep .ready signal files inherited from backup.
+# 000000010000000000000001.ready existed in the backup.
+ok( ! -f "$standby1_data/pg_wal/archive_status/000000010000000000000001.ready",
+  ".ready signal file existing in backup removed with archive_mode=on on standby" );
+
+# recovery with archive_mode=on should not create .ready signal files
+# 000000010000000000000002.ready did not exist in the backup
+ok( ! -f "$standby1_data/pg_wal/archive_status/000000010000000000000002.ready",
+  "standby doesn't create .ready signal file when archive_mode=on" );
+
+# recovery with archive_mode=on creates .done signal files
+ok( -f "$standby1_data/pg_wal/archive_status/000000010000000000000002.done",
+  "standby creates .done signal file when archive_mode=on" );
+
+# test recovery with archive_mode=always keeps .ready WALs
+$standby2 = get_new_node('standby2');
+$standby2->init_from_backup($node, 'backup', has_restoring => 1);
+$standby2->append_conf('postgresql.conf', 'archive_mode = always');
+$standby1->append_conf('postgresql.auto.conf', "archive_command = false");
+$standby2_data = $standby2->data_dir;
+$standby2->start;
+
+$standby2->safe_psql('postgres', q{CHECKPOINT});
+
+ok( -f "$standby2_data/pg_wal/archive_status/000000010000000000000001.ready",
+  ".ready signal file existing in backup are kept with archive_mode=always on standby" );
+
+ok( -f "$standby2_data/pg_wal/archive_status/000000010000000000000002.ready",
+  ".ready signal file are created with archive_mode=always on standby" );
+
+# Allow WAL archiving again
+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});
+
+is($standby2->safe_psql('postgres',
+		q{ SELECT failed_count, archived_count FROM pg_stat_archiver }),
+	'0|0',
+	'statistics reset from pg_stat_archiver succeed');
+
+# We need to crash the cluster because next test checks the crash
+# recovery step do not removes non-archived WAL on a standby.
+$standby2->stop('immediate');
+$standby2->start;
+
+ok( -f "$standby2_data/pg_wal/archive_status/000000010000000000000001.ready",
+  "WAL segment still ready to archive after crash recovery on standby with archive_mode=always");
+
+# Allow WAL archiving again
+$standby2->safe_psql('postgres', q{
+	ALTER SYSTEM RESET archive_command;
+	SELECT pg_reload_conf();
+});
+
+# wait for archive success
+$standby2->poll_query_until('postgres',
+	q{SELECT last_archived_wal FROM pg_stat_archiver},
+	'000000010000000000000002')  or die "Timed out while waiting for archiver to success";
+
+is($standby2->safe_psql('postgres',
+		q{SELECT archived_count FROM pg_stat_archiver}),
+	'2', 'WAL segment archived from standby');
+
+ok( ! -f "$standby2_data/pg_wal/archive_status/000000010000000000000001.ready"
+	&& ! -f "$standby2_data/pg_wal/archive_status/000000010000000000000002.ready",
+  ".ready signal file removed after archiving with archive_mode=always on standby" );
+
+ok( -f "$standby2_data/pg_wal/archive_status/000000010000000000000001.done"
+	and -f "$standby2_data/pg_wal/archive_status/000000010000000000000002.done",
+  ".done signal file created after archiving with archive_mode=always on standby" );
+
+#ok(0);
+#
+## wait for archive success
+#$standby2->poll_query_until('postgres',
+#	q{SELECT 1},
+#	'0')  or die "Timed out while waiting for archiver to success";
+