From: Michael Paquier <michael@paquier.xyz>
To: Jehan-Guillaume de Rorthais <jgdr@dalibo.com>
Cc: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Cc: masao.fujii@oss.nttdata.com
Cc: pgsql-bugs@lists.postgresql.org
Subject: Re: [BUG] non archived WAL removed during production crash recovery
Date: Wed, 22 Apr 2020 16:32:23 +0900
Message-ID: <20200422073223.GG33034@paquier.xyz> (raw)
In-Reply-To: <20200422011935.GF33034@paquier.xyz>
References: <20200417065043.GC350229@paquier.xyz>
<20200417153304.01a226cc@firost>
<20200418092611.GD350229@paquier.xyz>
<20200420.160231.719176619682386260.horikyota.ntt@gmail.com>
<20200420073444.GA77439@paquier.xyz>
<20200420142235.1536a73b@firost>
<20200421021501.GE77439@paquier.xyz>
<20200422004121.516a5a32@firost>
<20200422011935.GF33034@paquier.xyz>
On Wed, Apr 22, 2020 at 10:19:35AM +0900, Michael Paquier wrote:
> You are right here. The restriction can be removed, and I have
> checked that the test from v8 is able to pass on my Windows dev VM.
Attached are versions for each branch down to 9.5. While working on
the backpatch, I have not found major conflicts except one thing:
up to 10, Postgres does WAL segment recycling after two completed
checkpoints, and the 8th test of the script relies on the behavior of
11~ of one completed checkpoint (first .ready file present in the cold
backup but removed removed from $standby1). I have taken the simplest
approach to fix the test by checking that the .ready file actually
exists, while the rest of the test remains the same.
It is worth noting that for 9.5 and 9.6 the test had compatibility
issues with the renaming of pg_xlog to pg_wal, including paths and
functions. The calls to poll_query_until() also needed tweaks, but
I got the tests to work.
--
Michael
Attachments:
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-arch-master.patch (17.1K, ../20200422073223.GG33034@paquier.xyz/2-0001-Fix-handling-of-WAL-segments-ready-to-be-arch-master.patch)
download | inline diff:
From 8734b386e1e077be4d6e5353c08ab5a40b17e60f Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 214 ++++++++++++++++++++++
src/tools/pgindent/typedefs.list | 1 +
5 files changed, 286 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex f60ed2d36c..0a12afb59e 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_DONE /* 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.cindex 11e32733c4..009a071276 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_DONE. 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 still 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();
@@ -5166,7 +5177,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->SharedPromoteIsTriggered = false;
XLogCtl->WalWriterSleeping = false;
@@ -6871,7 +6882,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6884,6 +6901,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->checkPoint = checkPointLoc;
ControlFile->checkPointCopy = checkPoint;
@@ -7911,7 +7932,7 @@ StartupXLOG(void)
ControlFile->time = (pg_time_t) time(NULL);
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
UpdateControlFile();
@@ -8057,7 +8078,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -8069,8 +8090,8 @@ 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 +8107,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex d62c12310a..55becd65d4 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -572,18 +572,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..2369b34712--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,214 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_1 = "pg_wal/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count FROM pg_stat_archiver}, '1')+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_2 = "pg_wal/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ q{ SELECT last_archived_wal FROM pg_stat_archiver },+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on does not keep .ready signal files inherited+# from backup. Note that this WAL segment existed in the backup.+ok( !-f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup got removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ q{SELECT last_archived_wal FROM pg_stat_archiver},+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.listindex 525d58e7f0..b319266bb3 100644--- a/src/tools/pgindent/typedefs.list+++ b/src/tools/pgindent/typedefs.list@@ -1983,6 +1983,7 @@ RecordCacheEntry
RecordCompareData
RecordIOData
RecoveryLockListsEntry
+RecoveryState
RecoveryTargetTimeLineGoal
RecoveryTargetType
RectBox
--
2.26.0
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-archived-12.patch (16.7K, ../20200422073223.GG33034@paquier.xyz/3-0001-Fix-handling-of-WAL-segments-ready-to-be-archived-12.patch)
download | inline diff:
From 94fd9d2a5791a6ffe8bb3ace75a7e263fd91ff1c Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 214 ++++++++++++++++++++++
4 files changed, 285 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex d519252aad..d6ab348cb6 100644--- a/src/include/access/xlog.h+++ b/src/include/access/xlog.h@@ -164,6 +164,14 @@ 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_DONE /* currently in production */+} RecoveryState;+
extern PGDLLIMPORT int wal_level;
/* Is WAL archiving enabled (always or only while server is running normally)? */
@@ -277,6 +285,7 @@ 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.cindex 05cb6aa022..f181c4d144 100644--- a/src/backend/access/transam/xlog.c+++ b/src/backend/access/transam/xlog.c@@ -217,8 +217,9 @@ 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_DONE. True actually+ * means "not known, need to check the shared state".
*/
static bool LocalRecoveryInProgress = true;
@@ -643,10 +644,10 @@ typedef struct XLogCtlData
TimeLineID PrevTimeLineID;
/*
- * SharedRecoveryInProgress indicates if we're still in crash or archive+ * SharedRecoveryState indicates if we're still in crash or archive
* recovery. Protected by info_lck.
*/
- bool SharedRecoveryInProgress;+ RecoveryState SharedRecoveryState;
/*
* SharedHotStandbyActive indicates if we're still in crash or archive
@@ -4357,6 +4358,16 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, 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();
@@ -5069,7 +5080,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->WalWriterSleeping = false;
@@ -6758,7 +6769,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6771,6 +6788,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->checkPoint = checkPointLoc;
ControlFile->checkPointCopy = checkPoint;
@@ -7785,7 +7806,7 @@ StartupXLOG(void)
ControlFile->time = (pg_time_t) time(NULL);
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
UpdateControlFile();
@@ -7931,7 +7952,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -7943,8 +7964,8 @@ 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();
@@ -7960,6 +7981,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex e14bcf8ea6..b3e5338766 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -617,18 +617,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..2369b34712--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,214 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_1 = "pg_wal/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count FROM pg_stat_archiver}, '1')+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_2 = "pg_wal/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ q{ SELECT last_archived_wal FROM pg_stat_archiver },+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on does not keep .ready signal files inherited+# from backup. Note that this WAL segment existed in the backup.+ok( !-f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup got removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ q{SELECT last_archived_wal FROM pg_stat_archiver},+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);--
2.26.0
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-archived-11.patch (16.7K, ../20200422073223.GG33034@paquier.xyz/4-0001-Fix-handling-of-WAL-segments-ready-to-be-archived-11.patch)
download | inline diff:
From 9fa0d187375b7ce2ed15b527d42fd78ca1c70d42 Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 214 ++++++++++++++++++++++
4 files changed, 285 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex ef6aabde9f..1d9c87cb82 100644--- a/src/include/access/xlog.h+++ b/src/include/access/xlog.h@@ -129,6 +129,14 @@ 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_DONE /* currently in production */+} RecoveryState;+
extern PGDLLIMPORT int wal_level;
/* Is WAL archiving enabled (always or only while server is running normally)? */
@@ -243,6 +251,7 @@ 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.cindex 62f87ed174..0017bcf85b 100644--- a/src/backend/access/transam/xlog.c+++ b/src/backend/access/transam/xlog.c@@ -211,8 +211,9 @@ 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_DONE. True actually+ * means "not known, need to check the shared state".
*/
static bool LocalRecoveryInProgress = true;
@@ -637,10 +638,10 @@ typedef struct XLogCtlData
char archiveCleanupCommand[MAXPGPATH];
/*
- * SharedRecoveryInProgress indicates if we're still in crash or archive+ * SharedRecoveryState indicates if we're still in crash or archive
* recovery. Protected by info_lck.
*/
- bool SharedRecoveryInProgress;+ RecoveryState SharedRecoveryState;
/*
* SharedHotStandbyActive indicates if we're still in crash or archive
@@ -4306,6 +4307,16 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, 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();
@@ -5047,7 +5058,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->WalWriterSleeping = false;
@@ -6859,7 +6870,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6872,6 +6889,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->checkPoint = checkPointLoc;
ControlFile->checkPointCopy = checkPoint;
@@ -7896,7 +7917,7 @@ StartupXLOG(void)
ControlFile->time = (pg_time_t) time(NULL);
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
UpdateControlFile();
@@ -8042,7 +8063,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -8054,8 +8075,8 @@ 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();
@@ -8071,6 +8092,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex 2d2812b59c..f8b8504e41 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -610,18 +610,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..2369b34712--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,214 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_1 = "pg_wal/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count FROM pg_stat_archiver}, '1')+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_2 = "pg_wal/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ q{ SELECT last_archived_wal FROM pg_stat_archiver },+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on does not keep .ready signal files inherited+# from backup. Note that this WAL segment existed in the backup.+ok( !-f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup got removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ q{SELECT last_archived_wal FROM pg_stat_archiver},+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);--
2.26.0
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-archived-10.patch (16.7K, ../20200422073223.GG33034@paquier.xyz/5-0001-Fix-handling-of-WAL-segments-ready-to-be-archived-10.patch)
download | inline diff:
From 10809521faf22fa63f70d016f3f317796be5849d Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 215 ++++++++++++++++++++++
4 files changed, 286 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex 8751d86cbd..d41fefc185 100644--- a/src/include/access/xlog.h+++ b/src/include/access/xlog.h@@ -128,6 +128,14 @@ 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_DONE /* currently in production */+} RecoveryState;+
extern PGDLLIMPORT int wal_level;
/* Is WAL archiving enabled (always or only while server is running normally)? */
@@ -242,6 +250,7 @@ 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.cindex ec66b99b32..c10dc889c6 100644--- a/src/backend/access/transam/xlog.c+++ b/src/backend/access/transam/xlog.c@@ -209,8 +209,9 @@ 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_DONE. True actually+ * means "not known, need to check the shared state".
*/
static bool LocalRecoveryInProgress = true;
@@ -635,10 +636,10 @@ typedef struct XLogCtlData
char archiveCleanupCommand[MAXPGPATH];
/*
- * SharedRecoveryInProgress indicates if we're still in crash or archive+ * SharedRecoveryState indicates if we're still in crash or archive
* recovery. Protected by info_lck.
*/
- bool SharedRecoveryInProgress;+ RecoveryState SharedRecoveryState;
/*
* SharedHotStandbyActive indicates if we're still in crash or archive
@@ -4295,6 +4296,16 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, 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();
@@ -4980,7 +4991,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->WalWriterSleeping = false;
@@ -6803,7 +6814,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6816,6 +6833,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->prevCheckPoint = ControlFile->checkPoint;
ControlFile->checkPoint = checkPointLoc;
@@ -7841,7 +7862,7 @@ StartupXLOG(void)
ControlFile->time = (pg_time_t) time(NULL);
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
UpdateControlFile();
@@ -7987,7 +8008,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -7999,8 +8020,8 @@ 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();
@@ -8016,6 +8037,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex 7825cfe532..13f18ae85d 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -608,18 +608,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..390b85702b--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,215 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_1 = "pg_wal/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count FROM pg_stat_archiver}, '1')+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_walfile_name(pg_current_wal_lsn())});+my $segment_path_2 = "pg_wal/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_wal();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ q{ SELECT last_archived_wal FROM pg_stat_archiver },+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on keeps .ready signal files inherited+# from backup after one checkpoint. Note that this WAL segment+# existed in the backup.+ok( -f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup not removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ q{SELECT last_archived_wal FROM pg_stat_archiver},+ $segment_name_2)+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);--
2.26.0
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-archived-96.patch (16.7K, ../20200422073223.GG33034@paquier.xyz/6-0001-Fix-handling-of-WAL-segments-ready-to-be-archived-96.patch)
download | inline diff:
From d9baaf1b8f9ce9afec0b2c20610aaf64d05f4c5c Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 213 ++++++++++++++++++++++
4 files changed, 284 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex ab97a61bbb..28f716d4cf 100644--- a/src/include/access/xlog.h+++ b/src/include/access/xlog.h@@ -125,6 +125,14 @@ 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_DONE /* currently in production */+} RecoveryState;+
extern PGDLLIMPORT int wal_level;
/* Is WAL archiving enabled (always or only while server is running normally)? */
@@ -231,6 +239,7 @@ 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.cindex 823efdbed0..acca98ea28 100644--- a/src/backend/access/transam/xlog.c+++ b/src/backend/access/transam/xlog.c@@ -204,8 +204,9 @@ 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_DONE. True actually+ * means "not known, need to check the shared state".
*/
static bool LocalRecoveryInProgress = true;
@@ -616,10 +617,10 @@ typedef struct XLogCtlData
char archiveCleanupCommand[MAXPGPATH];
/*
- * SharedRecoveryInProgress indicates if we're still in crash or archive+ * SharedRecoveryState indicates if we're still in crash or archive
* recovery. Protected by info_lck.
*/
- bool SharedRecoveryInProgress;+ RecoveryState SharedRecoveryState;
/*
* SharedHotStandbyActive indicates if we're still in crash or archive
@@ -4136,6 +4137,16 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, 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();
@@ -4819,7 +4830,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->WalWriterSleeping = false;
@@ -6541,7 +6552,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6554,6 +6571,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->prevCheckPoint = ControlFile->checkPoint;
ControlFile->checkPoint = checkPointLoc;
@@ -7555,7 +7576,7 @@ StartupXLOG(void)
* updates to shared memory.)
*/
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
/*
@@ -7698,7 +7719,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -7710,8 +7731,8 @@ 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();
@@ -7727,6 +7748,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex 99704c1469..3cc8021cb8 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -619,18 +619,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..7cf367d8bf--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,213 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_xlogfile_name(pg_current_xlog_location())});+my $segment_path_1 = "pg_xlog/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_xlog();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count = 1 FROM pg_stat_archiver})+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_xlogfile_name(pg_current_xlog_location())});+my $segment_path_2 = "pg_xlog/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_xlog();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ qq{ SELECT last_archived_wal = '$segment_name_2' FROM pg_stat_archiver })+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on keeps .ready signal files inherited+# from backup after one checkpoint. Note that this WAL segment+# existed in the backup.+ok( -f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup not removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ qq{SELECT last_archived_wal = '$segment_name_2' FROM pg_stat_archiver})+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);--
2.26.0
[text/x-diff] 0001-Fix-handling-of-WAL-segments-ready-to-be-archived-95.patch (16.8K, ../20200422073223.GG33034@paquier.xyz/7-0001-Fix-handling-of-WAL-segments-ready-to-be-archived-95.patch)
download | inline diff:
From 3dd404655cdc1667f5b2274cfc30c4d24ff988de Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 22 Apr 2020 14:48:25 +0900
Subject: [PATCH] Fix handling of WAL segments ready to be archived during
crash recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
78ea8b5 has fixed an issue related to the recycling of WAL segments on
standbys depending on archive_mode. However, it has introduced a
regression with the handling of WAL segments ready to be archived during
crash recovery, causing those files to be recycled without getting
archived.
This commit fixes the regression by tracking in shared memory if a live
cluster is either in crash recovery or archive recovery as the handling
of WAL segments ready to be archived is different in both cases (those
WAL segments should not be removed during crash recovery), and by using
this new shared memory state to decide if a segment can be recycled or
not. Previously, it was not possible to know if a cluster was in crash
recovery or archive recovery as the shared state was able to track only
if recovery was happening or not, leading to the problem.
A set of TAP tests is added to close the gap here, making sure that WAL
segments ready to be archived are correctly handled when a cluster is in
archive or crash recovery with archive_mode set to "on" or "always", for
both standby and primary.
Reported-by: Benoît Lobréau
Author: Jehan-Guillaume de Rorthais
Reviewed-by: Kyotaro Horiguchi, Fujii Masao, Michael Paquier
Discussion: https://postgr.es/m/20200331172229.40ee00dc@firost
Backpatch-through: 9.5
---
src/include/access/xlog.h | 9 +
src/backend/access/transam/xlog.c | 57 +++++-
src/backend/access/transam/xlogarchive.c | 21 ++-
src/test/recovery/t/020_archive_status.pl | 213 ++++++++++++++++++++++
4 files changed, 284 insertions(+), 16 deletions(-)
create mode 100644 src/test/recovery/t/020_archive_status.pl
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.hindex 59ebccb19e..d051ee02bc 100644--- a/src/include/access/xlog.h+++ b/src/include/access/xlog.h@@ -126,6 +126,14 @@ typedef enum WalLevel
} WalLevel;
extern int wal_level;
+/* Recovery states */+typedef enum RecoveryState+{+ RECOVERY_STATE_CRASH = 0, /* crash recovery */+ RECOVERY_STATE_ARCHIVE, /* archive recovery */+ RECOVERY_STATE_DONE /* currently in production */+} RecoveryState;+
/* Is WAL archiving enabled (always or only while server is running normally)? */
#define XLogArchivingActive() \
(XLogArchiveMode > ARCHIVE_MODE_OFF && wal_level >= WAL_LEVEL_ARCHIVE)
@@ -230,6 +238,7 @@ 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.cindex a378df9d76..a6cdb0024f 100644--- a/src/backend/access/transam/xlog.c+++ b/src/backend/access/transam/xlog.c@@ -203,8 +203,9 @@ 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_DONE. True actually+ * means "not known, need to check the shared state".
*/
static bool LocalRecoveryInProgress = true;
@@ -608,10 +609,10 @@ typedef struct XLogCtlData
char archiveCleanupCommand[MAXPGPATH];
/*
- * SharedRecoveryInProgress indicates if we're still in crash or archive+ * SharedRecoveryState indicates if we're still in crash or archive
* recovery. Protected by info_lck.
*/
- bool SharedRecoveryInProgress;+ RecoveryState SharedRecoveryState;
/*
* SharedHotStandbyActive indicates if we're still in crash or archive
@@ -4083,6 +4084,16 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, 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();
@@ -4771,7 +4782,7 @@ XLOGShmemInit(void)
* in additional info.)
*/
XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
- XLogCtl->SharedRecoveryInProgress = true;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
XLogCtl->SharedHotStandbyActive = false;
XLogCtl->WalWriterSleeping = false;
@@ -6493,7 +6504,13 @@ StartupXLOG(void)
*/
dbstate_at_startup = ControlFile->state;
if (InArchiveRecovery)
+ {
ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;+ SpinLockRelease(&XLogCtl->info_lck);+ }
else
{
ereport(LOG,
@@ -6506,6 +6523,10 @@ StartupXLOG(void)
ControlFile->checkPointCopy.ThisTimeLineID,
recoveryTargetTLI)));
ControlFile->state = DB_IN_CRASH_RECOVERY;
++ SpinLockAcquire(&XLogCtl->info_lck);+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;+ SpinLockRelease(&XLogCtl->info_lck);
}
ControlFile->prevCheckPoint = ControlFile->checkPoint;
ControlFile->checkPoint = checkPointLoc;
@@ -7496,7 +7517,7 @@ StartupXLOG(void)
* updates to shared memory.)
*/
SpinLockAcquire(&XLogCtl->info_lck);
- XLogCtl->SharedRecoveryInProgress = false;+ XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
SpinLockRelease(&XLogCtl->info_lck);
/*
@@ -7639,7 +7660,7 @@ RecoveryInProgress(void)
*/
volatile XLogCtlData *xlogctl = XLogCtl;
- LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;+ LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
/*
* Initialize TimeLineID and RedoRecPtr when we discover that recovery
@@ -7651,8 +7672,8 @@ 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();
@@ -7668,6 +7689,24 @@ RecoveryInProgress(void)
}
}
+/*+ * Returns current recovery state from shared memory.+ *+ * This returned state is kept consistent with the contents of the control+ * file. 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.cindex c899594fb6..e36a85ccab 100644--- a/src/backend/access/transam/xlogarchive.c+++ b/src/backend/access/transam/xlogarchive.c@@ -619,18 +619,25 @@ 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;
/*
- * 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".+ * During archive recovery, the file is deletable if archive_mode is not+ * "always".
*/
- if (!((XLogArchivingActive() && !inRecovery) ||- (XLogArchivingAlways() && inRecovery)))+ if (!XLogArchivingAlways() &&+ GetRecoveryState() == RECOVERY_STATE_ARCHIVE)
return true;
+ /*+ * At this point of the logic, note that we are either a primary with+ * archive_mode set to "on" or "always", or a standby with archive_mode+ * set to "always".+ */+
/* First check for .done --- this means archiver is done with it */
StatusFilePath(archiveStatusPath, xlog, ".done");
if (stat(archiveStatusPath, &stat_buf) == 0)
diff --git a/src/test/recovery/t/020_archive_status.pl b/src/test/recovery/t/020_archive_status.plnew file mode 100644index 0000000000..7cf367d8bf--- /dev/null+++ b/src/test/recovery/t/020_archive_status.pl@@ -0,0 +1,213 @@+#+# Tests related to WAL archiving and recovery.+#+use strict;+use warnings;+use PostgresNode;+use TestLib;+use Test::More tests => 16;+use Config;++my $primary = get_new_node('master');+$primary->init(+ has_archiving => 1,+ allows_streaming => 1);+$primary->append_conf('postgresql.conf', 'autovacuum = off');+$primary->start;+my $primary_data = $primary->data_dir;++# Temporarily use an archive_command value to make the archiver fail,+# knowing that archiving is enabled. Note that we cannot use a command+# that does not exist as in this case the archiver process would just exit+# without reporting the failure to pg_stat_archiver. This also cannot+# use a plain "false" as that's unportable on Windows. So, instead, as+# a portable solution, use an archive command based on a command known to+# work but will fail: copy with an incorrect original path.+my $incorrect_command =+ $TestLib::windows_os+ ? qq{copy "%p_does_not_exist" "%f_does_not_exist"}+ : qq{cp "%p_does_not_exist" "%f_does_not_exist"};+$primary->safe_psql(+ 'postgres', qq{+ ALTER SYSTEM SET archive_command TO '$incorrect_command';+ SELECT pg_reload_conf();+});++# Save the WAL segment currently in use and switch to a new segment.+# This will be used to track the activity of the archiver.+my $segment_name_1 = $primary->safe_psql('postgres',+ q{SELECT pg_xlogfile_name(pg_current_xlog_location())});+my $segment_path_1 = "pg_xlog/archive_status/$segment_name_1";+my $segment_path_1_ready = "$segment_path_1.ready";+my $segment_path_1_done = "$segment_path_1.done";+$primary->safe_psql(+ 'postgres', q{+ CREATE TABLE mine AS SELECT generate_series(1,10) AS x;+ SELECT pg_switch_xlog();+ CHECKPOINT;+});++# Wait for an archive failure.+$primary->poll_query_until('postgres',+ q{SELECT failed_count > 0 FROM pg_stat_archiver}, 't')+ or die "Timed out while waiting for archiving to fail";+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file exists for WAL segment $segment_name_1 waiting to be archived"+);+ok( !-f "$primary_data/$segment_path_1_done",+ ".done file does not exist for WAL segment $segment_name_1 waiting to be archived"+);++is( $primary->safe_psql(+ 'postgres', q{+ SELECT archived_count, last_failed_wal+ FROM pg_stat_archiver+ }),+ "0|$segment_name_1",+ 'pg_stat_archiver failed to archive $segment_name_1');++# Crash the cluster for the next test in charge of checking that non-archived+# WAL segments are not removed.+$primary->stop('immediate');++# Recovery tests for the archiving with a standby partially check+# the recovery behavior when restoring a backup taken using 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. Note that the base backup+# is taken here so as archive_command will fail. This is necessary+# for the assumptions of the tests done with the standbys below.+$primary->backup_fs_cold('backup');++$primary->start;+ok( -f "$primary_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 still exists after crash recovery on primary"+);++# Allow WAL archiving again and wait for a success.+$primary->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});++$primary->poll_query_until('postgres',+ q{SELECT archived_count = 1 FROM pg_stat_archiver})+ or die "Timed out while waiting for archiving to finish";++ok(!-f "$primary_data/$segment_path_1_ready",+ ".ready file for archived WAL segment $segment_name_1 removed");++ok(-f "$primary_data/$segment_path_1_done",+ ".done file for archived WAL segment $segment_name_1 exists");++is( $primary->safe_psql(+ 'postgres', q{ SELECT last_archived_wal FROM pg_stat_archiver }),+ $segment_name_1,+ 'archive success reported in pg_stat_archiver for WAL segment $segment_name_1'+);++# Create some WAL activity and a new checkpoint so as the next standby can+# create a restartpoint. As this standby starts in crash recovery because+# of the cold backup taken previously, it needs a clean restartpoint to deal+# with existing status files.+my $segment_name_2 = $primary->safe_psql('postgres',+ q{SELECT pg_xlogfile_name(pg_current_xlog_location())});+my $segment_path_2 = "pg_xlog/archive_status/$segment_name_2";+my $segment_path_2_ready = "$segment_path_2.ready";+my $segment_path_2_done = "$segment_path_2.done";+$primary->safe_psql(+ 'postgres', q{+ INSERT INTO mine SELECT generate_series(10,20) AS x;+ SELECT pg_switch_xlog();+ CHECKPOINT;+});++$primary->poll_query_until('postgres',+ qq{ SELECT last_archived_wal = '$segment_name_2' FROM pg_stat_archiver })+ or die "Timed out while waiting for archiving to finish";++# Test standby with archive_mode = on.+my $standby1 = get_new_node('standby');+$standby1->init_from_backup($primary, 'backup', has_restoring => 1);+$standby1->append_conf('postgresql.conf', "archive_mode = on");+my $standby1_data = $standby1->data_dir;+$standby1->start;+$standby1->safe_psql('postgres', q{CHECKPOINT});++# Recovery with archive_mode=on keeps .ready signal files inherited+# from backup after one checkpoint. Note that this WAL segment+# existed in the backup.+ok( -f "$standby1_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 present in backup not removed with archive_mode=on on standby"+);++# Recovery with archive_mode=on should not create .ready files.+# Note that this segment did not exist in the backup.+ok( !-f "$standby1_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 not created on standby when archive_mode=on on standby"+);++# Recovery with archive_mode = on creates .done files.+ok( -f "$standby1_data/$segment_path_2_done",+ ".done file for WAL segment $segment_name_2 created when archive_mode=on on standby"+);++# Test recovery with archive_mode = always, which should always keep+# .ready files if archiving is enabled, though here we want the archive+# command to fail to persist the .ready files. Note that this node+# has inherited the archive command of the previous cold backup that+# will cause archiving failures.+my $standby2 = get_new_node('standby2');+$standby2->init_from_backup($primary, 'backup', has_restoring => 1);+$standby2->append_conf('postgresql.conf', 'archive_mode = always');+my $standby2_data = $standby2->data_dir;+$standby2->start;++$standby2->safe_psql('postgres', q{CHECKPOINT});++ok( -f "$standby2_data/$segment_path_1_ready",+ ".ready file for WAL segment $segment_name_1 existing in backup is kept with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_2_ready",+ ".ready file for WAL segment $segment_name_2 created with archive_mode=always on standby"+);++# Reset statistics of the archiver for the next checks.+$standby2->safe_psql('postgres', q{SELECT pg_stat_reset_shared('archiver')});++# Now crash the cluster to check that recovery step does not+# remove non-archived WAL segments on a standby where archiving+# is enabled.+$standby2->stop('immediate');+$standby2->start;++ok( -f "$standby2_data/$segment_path_1_ready",+ "WAL segment still ready to archive after crash recovery on standby with archive_mode=always"+);++# Allow WAL archiving again, and wait for the segments to be archived.+$standby2->safe_psql(+ 'postgres', q{+ ALTER SYSTEM RESET archive_command;+ SELECT pg_reload_conf();+});+$standby2->poll_query_until('postgres',+ qq{SELECT last_archived_wal = '$segment_name_2' FROM pg_stat_archiver})+ or die "Timed out while waiting for archiving to finish";++is( $standby2->safe_psql(+ 'postgres', q{SELECT archived_count FROM pg_stat_archiver}),+ '2',+ 'correct number of WAL segments archived from standby');++ok( !-f "$standby2_data/$segment_path_1_ready"+ && !-f "$standby2_data/$segment_path_2_ready",+ ".ready files removed after archive success with archive_mode=always on standby"+);++ok( -f "$standby2_data/$segment_path_1_done"+ && -f "$standby2_data/$segment_path_2_done",+ ".done files created after archive success with archive_mode=always on standby"+);--
2.26.0
[application/pgp-signature] signature.asc (832B, ../20200422073223.GG33034@paquier.xyz/8-signature.asc)
download
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-bugs@postgresql.org
Cc: michael@paquier.xyz, jgdr@dalibo.com, horikyota.ntt@gmail.com, masao.fujii@oss.nttdata.com, pgsql-bugs@lists.postgresql.org
Subject: Re: [BUG] non archived WAL removed during production crash recovery
In-Reply-To: <20200422073223.GG33034@paquier.xyz>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox