public inbox for [email protected]
help / color / mirror / Atom feedFrom: shveta malik <[email protected]>
To: Zhijie Hou (Fujitsu) <[email protected]>
Cc: Amit Kapila <[email protected]>
Cc: Masahiko Sawada <[email protected]>
Cc: Drouvot, Bertrand <[email protected]>
Cc: Peter Smith <[email protected]>
Cc: Nisha Moond <[email protected]>
Cc: Hayato Kuroda (Fujitsu) <[email protected]>
Cc: Bharath Rupireddy <[email protected]>
Cc: Peter Eisentraut <[email protected]>
Cc: Bruce Momjian <[email protected]>
Cc: Ashutosh Sharma <[email protected]>
Cc: Andres Freund <[email protected]>
Cc: pgsql-hackers <[email protected]>
Cc: Ajin Cherian <[email protected]>
Cc: Alvaro Herrera <[email protected]>
Cc: shveta malik <[email protected]>
Subject: Re: Synchronizing slots from primary to standby
Date: Thu, 4 Jan 2024 10:27:31 +0530
Message-ID: <CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com> (raw)
In-Reply-To: <CAJpy0uDhR=m2Pr76aJZnvtKZpCEiLbMbjbPReCv5fS0MA3ch2w@mail.gmail.com>
References: <CAA4eK1+AFY4E0f9h0-JF-navrf-vRMTMrN6H7PDKiR=C6p84Nw@mail.gmail.com>
<CAJpy0uCcFKiofcp5V_hRvHrY_qVNX+eKvB0CPDNxSk2FbyMJCA@mail.gmail.com>
<OS0PR01MB5716E731AC1B97A96B014B929460A@OS0PR01MB5716.jpnprd01.prod.outlook.com>
<CAJpy0uDhR=m2Pr76aJZnvtKZpCEiLbMbjbPReCv5fS0MA3ch2w@mail.gmail.com>
On Thu, Jan 4, 2024 at 9:18 AM shveta malik <[email protected]> wrote:
>
> On Wed, Jan 3, 2024 at 6:33 PM Zhijie Hou (Fujitsu)
> <[email protected]> wrote:
> >
> > On Tuesday, January 2, 2024 6:32 PM shveta malik <[email protected]> wrote:
> > > On Fri, Dec 29, 2023 at 10:25 AM Amit Kapila <[email protected]>
> > >
> > > The topup patch has also changed app_name to
> > > {cluster_name}_slotsyncworker so that we do not confuse between walreceiver
> > > and slotsyncworker entry.
> > >
> > > Please note that there is no change in rest of the patches, changes are in
> > > additional 0004 patch alone.
> >
> > Attach the V56 patch set which supports ALTER SUBSCRIPTION SET (failover).
> > This is useful when user want to refresh the publication tables, they can now alter the
> > failover option to false and then execute the refresh command.
> >
> > Best Regards,
> > Hou zj
>
> The patches no longer apply to HEAD due to a recent commit 007693f. I
> am working on rebasing and will post the new patches soon
>
> thanks
> Shveta
Commit 007693f has changed 'conflicting' to 'conflict_reason', so
adjusted the code around that in the slotsync worker.
Also removed function 'pg_get_slot_invalidation_cause' as now
conflict_reason tells the same.
PFA rebased patches with above changes.
thanks
Shveta
Attachments:
[application/octet-stream] v57-0004-Non-replication-connection-and-app_name-change.patch (8.6K, ../CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com/2-v57-0004-Non-replication-connection-and-app_name-change.patch)
download | inline diff:
From f6db2a8e9277858499608e19c7a38ca8c0941127 Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Fri, 29 Dec 2023 13:15:15 +0530
Subject: [PATCH v57 4/4] Non replication connection and app_name change.
Changes in this patch:
1) Convert replication connection to non-replication one in slotsync worker.
2) Use app_name as {cluster_name}_slotsyncworker in the slotsync worker
connection.
---
src/backend/commands/subscriptioncmds.c | 8 ++---
.../libpqwalreceiver/libpqwalreceiver.c | 35 ++++++++++++-------
src/backend/replication/logical/slotsync.c | 13 +++++--
src/backend/replication/logical/tablesync.c | 2 +-
src/backend/replication/logical/worker.c | 2 +-
src/backend/replication/walreceiver.c | 2 +-
src/include/replication/walreceiver.h | 5 +--
7 files changed, 44 insertions(+), 23 deletions(-)
diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index c76898d3ae..0aeb2ecc13 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -755,7 +755,7 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
/* Try to connect to the publisher. */
must_use_password = !superuser_arg(owner) && opts.passwordrequired;
- wrconn = walrcv_connect(conninfo, true, must_use_password,
+ wrconn = walrcv_connect(conninfo, true, true, must_use_password,
stmt->subname, &err);
if (!wrconn)
ereport(ERROR,
@@ -926,7 +926,7 @@ AlterSubscription_refresh(Subscription *sub, bool copy_data,
/* Try to connect to the publisher. */
must_use_password = sub->passwordrequired && !sub->ownersuperuser;
- wrconn = walrcv_connect(sub->conninfo, true, must_use_password,
+ wrconn = walrcv_connect(sub->conninfo, true, true, must_use_password,
sub->name, &err);
if (!wrconn)
ereport(ERROR,
@@ -1607,7 +1607,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
/* Try to connect to the publisher. */
must_use_password = sub->passwordrequired && !sub->ownersuperuser;
- wrconn = walrcv_connect(sub->conninfo, true, must_use_password,
+ wrconn = walrcv_connect(sub->conninfo, true, true, must_use_password,
sub->name, &err);
if (!wrconn)
ereport(ERROR,
@@ -1858,7 +1858,7 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
*/
load_file("libpqwalreceiver", false);
- wrconn = walrcv_connect(conninfo, true, must_use_password,
+ wrconn = walrcv_connect(conninfo, true, true, must_use_password,
subname, &err);
if (wrconn == NULL)
{
diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
index 7a6ff557bc..8b1477cdc1 100644
--- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
+++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
@@ -50,7 +50,8 @@ struct WalReceiverConn
/* Prototypes for interface functions */
static WalReceiverConn *libpqrcv_connect(const char *conninfo,
- bool logical, bool must_use_password,
+ bool replication, bool logical,
+ bool must_use_password,
const char *appname, char **err);
static void libpqrcv_check_conninfo(const char *conninfo,
bool must_use_password);
@@ -136,8 +137,8 @@ _PG_init(void)
* case.
*/
static WalReceiverConn *
-libpqrcv_connect(const char *conninfo, bool logical, bool must_use_password,
- const char *appname, char **err)
+libpqrcv_connect(const char *conninfo, bool replication, bool logical,
+ bool must_use_password, const char *appname, char **err)
{
WalReceiverConn *conn;
const char *keys[6];
@@ -150,17 +151,27 @@ libpqrcv_connect(const char *conninfo, bool logical, bool must_use_password,
*/
keys[i] = "dbname";
vals[i] = conninfo;
- keys[++i] = "replication";
- vals[i] = logical ? "database" : "true";
- if (!logical)
+
+ /* We can not have logical w/o replication */
+ if(!replication)
+ Assert(!logical);
+
+ if (replication)
{
- /*
- * The database name is ignored by the server in replication mode, but
- * specify "replication" for .pgpass lookup.
- */
- keys[++i] = "dbname";
- vals[i] = "replication";
+ keys[++i] = "replication";
+ vals[i] = logical ? "database" : "true";
+
+ if (!logical)
+ {
+ /*
+ * The database name is ignored by the server in replication mode,
+ * but specify "replication" for .pgpass lookup.
+ */
+ keys[++i] = "dbname";
+ vals[i] = "replication";
+ }
}
+
keys[++i] = "fallback_application_name";
vals[i] = appname;
if (logical)
diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c
index a84ab020ee..df30a0c8b4 100644
--- a/src/backend/replication/logical/slotsync.c
+++ b/src/backend/replication/logical/slotsync.c
@@ -1126,6 +1126,7 @@ ReplSlotSyncWorkerMain(Datum main_arg)
char *dbname;
bool am_cascading_standby;
char *err;
+ StringInfoData app_name;
ereport(LOG, errmsg("replication slot sync worker started"));
@@ -1158,13 +1159,21 @@ ReplSlotSyncWorkerMain(Datum main_arg)
*/
BackgroundWorkerInitializeConnection(dbname, NULL, 0);
+ initStringInfo(&app_name);
+ if (cluster_name[0])
+ appendStringInfo(&app_name, "%s_%s", cluster_name, "slotsyncworker");
+ else
+ appendStringInfo(&app_name, "%s", "slotsyncworker");
+
/*
* Establish the connection to the primary server for slots
* synchronization.
*/
- wrconn = walrcv_connect(PrimaryConnInfo, true, false,
- cluster_name[0] ? cluster_name : "slotsyncworker",
+ wrconn = walrcv_connect(PrimaryConnInfo, false, false, false,
+ app_name.data,
&err);
+ pfree(app_name.data);
+
if (wrconn == NULL)
ereport(ERROR,
errcode(ERRCODE_CONNECTION_FAILURE),
diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c
index 74e9cfce1b..6587229680 100644
--- a/src/backend/replication/logical/tablesync.c
+++ b/src/backend/replication/logical/tablesync.c
@@ -1342,7 +1342,7 @@ LogicalRepSyncTableStart(XLogRecPtr *origin_startpos)
* so that synchronous replication can distinguish them.
*/
LogRepWorkerWalRcvConn =
- walrcv_connect(MySubscription->conninfo, true,
+ walrcv_connect(MySubscription->conninfo, true, true,
must_use_password,
slotname, &err);
if (LogRepWorkerWalRcvConn == NULL)
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 287412e1a6..e706fd8d0d 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -4554,7 +4554,7 @@ run_apply_worker()
must_use_password = MySubscription->passwordrequired &&
!MySubscription->ownersuperuser;
- LogRepWorkerWalRcvConn = walrcv_connect(MySubscription->conninfo, true,
+ LogRepWorkerWalRcvConn = walrcv_connect(MySubscription->conninfo, true, true,
must_use_password,
MySubscription->name, &err);
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index ffacd55e5c..f34ab09ac6 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -296,7 +296,7 @@ WalReceiverMain(void)
sigprocmask(SIG_SETMASK, &UnBlockSig, NULL);
/* Establish the connection to the primary for XLOG streaming */
- wrconn = walrcv_connect(conninfo, false, false,
+ wrconn = walrcv_connect(conninfo, true, false, false,
cluster_name[0] ? cluster_name : "walreceiver",
&err);
if (!wrconn)
diff --git a/src/include/replication/walreceiver.h b/src/include/replication/walreceiver.h
index 9f78fd1e5a..6c5681ab5b 100644
--- a/src/include/replication/walreceiver.h
+++ b/src/include/replication/walreceiver.h
@@ -237,6 +237,7 @@ typedef struct WalRcvExecResult
* returned with 'err' including the error generated.
*/
typedef WalReceiverConn *(*walrcv_connect_fn) (const char *conninfo,
+ bool replication,
bool logical,
bool must_use_password,
const char *appname,
@@ -434,8 +435,8 @@ typedef struct WalReceiverFunctionsType
extern PGDLLIMPORT WalReceiverFunctionsType *WalReceiverFunctions;
-#define walrcv_connect(conninfo, logical, must_use_password, appname, err) \
- WalReceiverFunctions->walrcv_connect(conninfo, logical, must_use_password, appname, err)
+#define walrcv_connect(conninfo, replication, logical, must_use_password, appname, err) \
+ WalReceiverFunctions->walrcv_connect(conninfo, replication, logical, must_use_password, appname, err)
#define walrcv_check_conninfo(conninfo, must_use_password) \
WalReceiverFunctions->walrcv_check_conninfo(conninfo, must_use_password)
#define walrcv_get_conninfo(conn) \
--
2.34.1
[application/octet-stream] v57-0003-Allow-logical-walsenders-to-wait-for-the-physica.patch (44.3K, ../CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com/3-v57-0003-Allow-logical-walsenders-to-wait-for-the-physica.patch)
download | inline diff:
From 12ee484de25498b71e20d12ddf53379bc9c53c80 Mon Sep 17 00:00:00 2001
From: Hou Zhijie <[email protected]>
Date: Wed, 3 Jan 2024 20:25:08 +0800
Subject: [PATCH v57 3/4] Allow logical walsenders to wait for the physical
standbys
This patch introduces a mechanism to ensure that physical standby servers,
which are potential failover candidates, have received and flushed changes
before making them visible to subscribers. By doing so, it guarantees that
the promoted standby server is not lagging behind the subscribers when a
failover is necessary.
A new parameter named standby_slot_names is introduced. The logical
walsender now guarantees that all local changes are sent and flushed to
the standby servers corresponding to the replication slots specified in
standby_slot_names before sending those changes to the subscriber.
Additionally, The SQL functions pg_logical_slot_get_changes and
pg_replication_slot_advance are modified to wait for the replication slots
mentioned in standby_slot_names to catch up before returning the changes
to the user.
---
doc/src/sgml/config.sgml | 24 ++
.../replication/logical/logicalfuncs.c | 13 +
src/backend/replication/slot.c | 342 +++++++++++++++++-
src/backend/replication/slotfuncs.c | 9 +
src/backend/replication/walsender.c | 111 +++++-
.../utils/activity/wait_event_names.txt | 1 +
src/backend/utils/misc/guc_tables.c | 14 +
src/backend/utils/misc/postgresql.conf.sample | 2 +
src/include/replication/slot.h | 7 +
src/include/replication/walsender.h | 1 +
src/include/replication/walsender_private.h | 7 +
src/include/utils/guc_hooks.h | 3 +
src/test/recovery/meson.build | 1 +
src/test/recovery/t/006_logical_decoding.pl | 3 +-
.../t/050_standby_failover_slots_sync.pl | 303 +++++++++++++---
15 files changed, 771 insertions(+), 70 deletions(-)
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index cd9ae70c41..57bb193757 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4419,6 +4419,30 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows
</listitem>
</varlistentry>
+ <varlistentry id="guc-standby-slot-names" xreflabel="standby_slot_names">
+ <term><varname>standby_slot_names</varname> (<type>string</type>)
+ <indexterm>
+ <primary><varname>standby_slot_names</varname> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ List of physical slots guarantees that logical replication slots with
+ failover enabled do not consume changes until those changes are received
+ and flushed to corresponding physical standbys. If a logical replication
+ connection is meant to switch to a physical standby after the standby is
+ promoted, the physical replication slot for the standby should be listed
+ here.
+ </para>
+ <para>
+ The standbys corresponding to the physical replication slots in
+ <varname>standby_slot_names</varname> must configure
+ <literal>enable_syncslot = true</literal> so they can receive
+ failover logical slots changes from the primary.
+ </para>
+ </listitem>
+ </varlistentry>
+
</variablelist>
</sect2>
diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c
index b0081d3ce5..5ff761dd65 100644
--- a/src/backend/replication/logical/logicalfuncs.c
+++ b/src/backend/replication/logical/logicalfuncs.c
@@ -30,6 +30,7 @@
#include "replication/decode.h"
#include "replication/logical.h"
#include "replication/message.h"
+#include "replication/walsender.h"
#include "storage/fd.h"
#include "utils/array.h"
#include "utils/builtins.h"
@@ -109,6 +110,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin
MemoryContext per_query_ctx;
MemoryContext oldcontext;
XLogRecPtr end_of_wal;
+ XLogRecPtr wait_for_wal_lsn;
LogicalDecodingContext *ctx;
ResourceOwner old_resowner = CurrentResourceOwner;
ArrayType *arr;
@@ -228,6 +230,17 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin
NameStr(MyReplicationSlot->data.plugin),
format_procedure(fcinfo->flinfo->fn_oid))));
+ if (XLogRecPtrIsInvalid(upto_lsn))
+ wait_for_wal_lsn = end_of_wal;
+ else
+ wait_for_wal_lsn = Min(upto_lsn, end_of_wal);
+
+ /*
+ * Wait for specified streaming replication standby servers (if any)
+ * to confirm receipt of WAL up to wait_for_wal_lsn.
+ */
+ WaitForStandbyConfirmation(wait_for_wal_lsn);
+
ctx->output_writer_private = p;
/*
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 9d27593979..5771209b9a 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -46,13 +46,18 @@
#include "common/string.h"
#include "miscadmin.h"
#include "pgstat.h"
+#include "postmaster/interrupt.h"
#include "replication/slot.h"
#include "replication/walsender.h"
+#include "replication/walsender_private.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "utils/builtins.h"
+#include "utils/guc_hooks.h"
+#include "utils/memutils.h"
+#include "utils/varlena.h"
/*
* Replication slot on-disk data structure.
@@ -99,10 +104,19 @@ ReplicationSlotCtlData *ReplicationSlotCtl = NULL;
/* My backend's replication slot in the shared memory array */
ReplicationSlot *MyReplicationSlot = NULL;
-/* GUC variable */
+/* GUC variables */
int max_replication_slots = 10; /* the maximum number of replication
* slots */
+/*
+ * This GUC lists streaming replication standby server slot names that
+ * logical WAL sender processes will wait for.
+ */
+char *standby_slot_names;
+
+/* This is parsed and cached list for raw standby_slot_names. */
+static List *standby_slot_names_list = NIL;
+
static void ReplicationSlotShmemExit(int code, Datum arg);
static void ReplicationSlotDropPtr(ReplicationSlot *slot);
@@ -2217,3 +2231,329 @@ RestoreSlotFromDisk(const char *name)
(errmsg("too many replication slots active before shutdown"),
errhint("Increase max_replication_slots and try again.")));
}
+
+/*
+ * A helper function to validate slots specified in GUC standby_slot_names.
+ */
+static bool
+validate_standby_slots(char **newval)
+{
+ char *rawname;
+ List *elemlist;
+ ListCell *lc;
+ bool ok;
+
+ /* Need a modifiable copy of string */
+ rawname = pstrdup(*newval);
+
+ /* Verify syntax and parse string into a list of identifiers */
+ ok = SplitIdentifierString(rawname, ',', &elemlist);
+
+ if (!ok)
+ GUC_check_errdetail("List syntax is invalid.");
+
+ /*
+ * If there is a syntax error in the name or if the replication slots'
+ * data is not initialized yet (i.e., we are in the startup process), skip
+ * the slot verification.
+ */
+ if (!ok || !ReplicationSlotCtl)
+ {
+ pfree(rawname);
+ list_free(elemlist);
+ return ok;
+ }
+
+ foreach(lc, elemlist)
+ {
+ char *name = lfirst(lc);
+ ReplicationSlot *slot;
+
+ slot = SearchNamedReplicationSlot(name, true);
+
+ if (!slot)
+ {
+ GUC_check_errdetail("replication slot \"%s\" does not exist",
+ name);
+ ok = false;
+ break;
+ }
+
+ if (!SlotIsPhysical(slot))
+ {
+ GUC_check_errdetail("\"%s\" is not a physical replication slot",
+ name);
+ ok = false;
+ break;
+ }
+ }
+
+ pfree(rawname);
+ list_free(elemlist);
+ return ok;
+}
+
+/*
+ * GUC check_hook for standby_slot_names
+ */
+bool
+check_standby_slot_names(char **newval, void **extra, GucSource source)
+{
+ if (strcmp(*newval, "") == 0)
+ return true;
+
+ /*
+ * "*" is not accepted as in that case primary will not be able to know
+ * for which all standbys to wait for. Even if we have physical-slots
+ * info, there is no way to confirm whether there is any standby
+ * configured for the known physical slots.
+ */
+ if (strcmp(*newval, "*") == 0)
+ {
+ GUC_check_errdetail("\"%s\" is not accepted for standby_slot_names",
+ *newval);
+ return false;
+ }
+
+ /* Now verify if the specified slots really exist and have correct type */
+ if (!validate_standby_slots(newval))
+ return false;
+
+ *extra = guc_strdup(ERROR, *newval);
+
+ return true;
+}
+
+/*
+ * GUC assign_hook for standby_slot_names
+ */
+void
+assign_standby_slot_names(const char *newval, void *extra)
+{
+ List *standby_slots;
+ MemoryContext oldcxt;
+ char *standby_slot_names_cpy = extra;
+
+ list_free(standby_slot_names_list);
+ standby_slot_names_list = NIL;
+
+ /* No value is specified for standby_slot_names. */
+ if (standby_slot_names_cpy == NULL)
+ return;
+
+ if (!SplitIdentifierString(standby_slot_names_cpy, ',', &standby_slots))
+ {
+ /* This should not happen if GUC checked check_standby_slot_names. */
+ elog(ERROR, "invalid list syntax");
+ }
+
+ /*
+ * Switch to the same memory context under which GUC variables are
+ * allocated (GUCMemoryContext).
+ */
+ oldcxt = MemoryContextSwitchTo(GetMemoryChunkContext(standby_slot_names_cpy));
+ standby_slot_names_list = list_copy(standby_slots);
+ MemoryContextSwitchTo(oldcxt);
+}
+
+/*
+ * Return a copy of standby_slot_names_list if the copy flag is set to true,
+ * otherwise return the original list.
+ */
+List *
+GetStandbySlotList(bool copy)
+{
+ /*
+ * Since we do not support syncing slots to cascading standbys, we return
+ * NIL here if we are running in a standby to indicate that no standby
+ * slots need to be waited for.
+ */
+ if (RecoveryInProgress())
+ return NIL;
+
+ if (copy)
+ return list_copy(standby_slot_names_list);
+ else
+ return standby_slot_names_list;
+}
+
+/*
+ * Reload the config file and reinitialize the standby slot list if the GUC
+ * standby_slot_names has changed.
+ */
+void
+RereadConfigAndReInitSlotList(List **standby_slots)
+{
+ char *pre_standby_slot_names;
+
+ /*
+ * If we are running on a standby, there is no need to reload
+ * standby_slot_names since we do not support syncing slots to cascading
+ * standbys.
+ */
+ if (RecoveryInProgress())
+ {
+ ProcessConfigFile(PGC_SIGHUP);
+ return;
+ }
+
+ pre_standby_slot_names = pstrdup(standby_slot_names);
+
+ ProcessConfigFile(PGC_SIGHUP);
+
+ if (strcmp(pre_standby_slot_names, standby_slot_names) != 0)
+ {
+ list_free(*standby_slots);
+ *standby_slots = GetStandbySlotList(true);
+ }
+
+ pfree(pre_standby_slot_names);
+}
+
+/*
+ * Filter the standby slots based on the specified log sequence number
+ * (wait_for_lsn).
+ *
+ * This function updates the passed standby_slots list, removing any slots that
+ * have already caught up to or surpassed the given wait_for_lsn. Additionally,
+ * it removes slots that have been invalidated, dropped, or converted to
+ * logical slots.
+ */
+void
+FilterStandbySlots(XLogRecPtr wait_for_lsn, List **standby_slots)
+{
+ ListCell *lc;
+ List *standby_slots_cpy = *standby_slots;
+
+ foreach(lc, standby_slots_cpy)
+ {
+ char *name = lfirst(lc);
+ char *warningfmt = NULL;
+ ReplicationSlot *slot;
+
+ slot = SearchNamedReplicationSlot(name, true);
+
+ if (!slot)
+ {
+ /*
+ * It may happen that the slot specified in standby_slot_names GUC
+ * value is dropped, so let's skip over it.
+ */
+ warningfmt = _("replication slot \"%s\" specified in parameter \"%s\" does not exist, ignoring");
+ }
+ else if (SlotIsLogical(slot))
+ {
+ /*
+ * If a logical slot name is provided in standby_slot_names, issue
+ * a WARNING and skip it. Although logical slots are disallowed in
+ * the GUC check_hook(validate_standby_slots), it is still
+ * possible for a user to drop an existing physical slot and
+ * recreate a logical slot with the same name. Since it is
+ * harmless, a WARNING should be enough, no need to error-out.
+ */
+ warningfmt = _("cannot have logical replication slot \"%s\" in parameter \"%s\", ignoring");
+ }
+ else
+ {
+ SpinLockAcquire(&slot->mutex);
+
+ if (slot->data.invalidated != RS_INVAL_NONE)
+ {
+ /*
+ * Specified physical slot have been invalidated, so no point
+ * in waiting for it.
+ */
+ warningfmt = _("physical slot \"%s\" specified in parameter \"%s\" has been invalidated, ignoring");
+ }
+ else if (XLogRecPtrIsInvalid(slot->data.restart_lsn) ||
+ slot->data.restart_lsn < wait_for_lsn)
+ {
+ bool inactive = (slot->active_pid == 0);
+
+ SpinLockRelease(&slot->mutex);
+
+ /* Log warning if no active_pid for this physical slot */
+ if (inactive)
+ ereport(WARNING,
+ errmsg("replication slot \"%s\" specified in parameter \"%s\" does not have active_pid",
+ name, "standby_slot_names"),
+ errdetail("Logical replication is waiting on the "
+ "standby associated with \"%s\".", name),
+ errhint("Consider starting standby associated with "
+ "\"%s\" or amend standby_slot_names.", name));
+
+ /* Continue if the current slot hasn't caught up. */
+ continue;
+ }
+ else
+ {
+ Assert(slot->data.restart_lsn >= wait_for_lsn);
+ }
+
+ SpinLockRelease(&slot->mutex);
+ }
+
+ /*
+ * Reaching here indicates that either the slot has passed the
+ * wait_for_lsn or there is an issue with the slot that requires a
+ * warning to be reported.
+ */
+ if (warningfmt)
+ ereport(WARNING, errmsg(warningfmt, name, "standby_slot_names"));
+
+ standby_slots_cpy = foreach_delete_current(standby_slots_cpy, lc);
+ }
+
+ *standby_slots = standby_slots_cpy;
+}
+
+/*
+ * Wait for physical standby to confirm receiving the given lsn.
+ *
+ * Used by logical decoding SQL functions that acquired slot with failover
+ * enabled. It waits for physical standbys corresponding to the physical slots
+ * specified in the standby_slot_names GUC.
+ */
+void
+WaitForStandbyConfirmation(XLogRecPtr wait_for_lsn)
+{
+ List *standby_slots;
+
+ if (!MyReplicationSlot->data.failover)
+ return;
+
+ standby_slots = GetStandbySlotList(true);
+
+ if (standby_slots == NIL)
+ return;
+
+ ConditionVariablePrepareToSleep(&WalSndCtl->wal_confirm_rcv_cv);
+
+ for (;;)
+ {
+ CHECK_FOR_INTERRUPTS();
+
+ if (ConfigReloadPending)
+ {
+ ConfigReloadPending = false;
+ RereadConfigAndReInitSlotList(&standby_slots);
+ }
+
+ FilterStandbySlots(wait_for_lsn, &standby_slots);
+
+ /* Exit if done waiting for every slot. */
+ if (standby_slots == NIL)
+ break;
+
+ /*
+ * We wait for the slots in the standby_slot_names to catch up, but we
+ * use a timeout so we can also check the if the standby_slot_names has
+ * been changed.
+ */
+ ConditionVariableTimedSleep(&WalSndCtl->wal_confirm_rcv_cv, 1000,
+ WAIT_EVENT_WAIT_FOR_STANDBY_CONFIRMATION);
+ }
+
+ ConditionVariableCancelSleep();
+ list_free(standby_slots);
+}
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index b59d6e62fd..71b50d3208 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -21,6 +21,7 @@
#include "replication/decode.h"
#include "replication/logical.h"
#include "replication/slot.h"
+#include "replication/walsender.h"
#include "utils/builtins.h"
#include "utils/inval.h"
#include "utils/pg_lsn.h"
@@ -487,6 +488,8 @@ pg_physical_replication_slot_advance(XLogRecPtr moveto)
* crash, but this makes the data consistent after a clean shutdown.
*/
ReplicationSlotMarkDirty();
+
+ PhysicalWakeupLogicalWalSnd();
}
return retlsn;
@@ -527,6 +530,12 @@ pg_logical_replication_slot_advance(XLogRecPtr moveto)
.segment_close = wal_segment_close),
NULL, NULL, NULL);
+ /*
+ * Wait for specified streaming replication standby servers (if any)
+ * to confirm receipt of WAL up to moveto lsn.
+ */
+ WaitForStandbyConfirmation(moveto);
+
/*
* Start reading at the slot's restart_lsn, which we know to point to
* a valid record.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 9d8710f904..2fcd864b28 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1219,7 +1219,6 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
parseCreateReplSlotOptions(cmd, &reserve_wal, &snapshot_action, &two_phase,
&failover);
-
if (cmd->kind == REPLICATION_KIND_PHYSICAL)
{
ReplicationSlotCreate(cmd->slotname, false,
@@ -1731,27 +1730,78 @@ WalSndUpdateProgress(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId
ProcessPendingWrites();
}
+/*
+ * Wake up the logical walsender processes with failover-enabled slots if the
+ * currently acquired physical slot is specified in standby_slot_names
+ * GUC.
+ */
+void
+PhysicalWakeupLogicalWalSnd(void)
+{
+ ListCell *lc;
+ List *standby_slots;
+
+ Assert(MyReplicationSlot && SlotIsPhysical(MyReplicationSlot));
+
+ standby_slots = GetStandbySlotList(false);
+
+ foreach(lc, standby_slots)
+ {
+ char *name = lfirst(lc);
+
+ if (strcmp(name, NameStr(MyReplicationSlot->data.name)) == 0)
+ {
+ ConditionVariableBroadcast(&WalSndCtl->wal_confirm_rcv_cv);
+ return;
+ }
+ }
+}
+
/*
* Wait till WAL < loc is flushed to disk so it can be safely sent to client.
*
- * Returns end LSN of flushed WAL. Normally this will be >= loc, but
- * if we detect a shutdown request (either from postmaster or client)
- * we will return early, so caller must always check.
+ * If the walsender holds a logical slot that has enabled failover, we also
+ * wait for all the specified streaming replication standby servers to
+ * confirm receipt of WAL up to RecentFlushPtr.
+ *
+ * Returns end LSN of flushed WAL. Normally this will be >= loc, but if we
+ * detect a shutdown request (either from postmaster or client) we will return
+ * early, so caller must always check.
*/
static XLogRecPtr
WalSndWaitForWal(XLogRecPtr loc)
{
int wakeEvents;
+ bool wait_for_standby = false;
+ uint32 wait_event;
+ List *standby_slots = NIL;
static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
+ if (MyReplicationSlot->data.failover)
+ standby_slots = GetStandbySlotList(true);
+
/*
- * Fast path to avoid acquiring the spinlock in case we already know we
- * have enough WAL available. This is particularly interesting if we're
- * far behind.
+ * Check if all the standby servers have confirmed receipt of WAL up to
+ * RecentFlushPtr even when we already know we have enough WAL available.
+ *
+ * Note that we cannot directly return without checking the status of
+ * standby servers because the standby_slot_names may have changed, which
+ * means there could be new standby slots in the list that have not yet
+ * caught up to the RecentFlushPtr.
*/
- if (RecentFlushPtr != InvalidXLogRecPtr &&
- loc <= RecentFlushPtr)
- return RecentFlushPtr;
+ if (!XLogRecPtrIsInvalid(RecentFlushPtr) && loc <= RecentFlushPtr)
+ {
+ FilterStandbySlots(RecentFlushPtr, &standby_slots);
+
+ /*
+ * Fast path to avoid acquiring the spinlock in case we already know
+ * we have enough WAL available and all the standby servers have
+ * confirmed receipt of WAL up to RecentFlushPtr. This is particularly
+ * interesting if we're far behind.
+ */
+ if (standby_slots == NIL)
+ return RecentFlushPtr;
+ }
/* Get a more recent flush pointer. */
if (!RecoveryInProgress())
@@ -1772,7 +1822,7 @@ WalSndWaitForWal(XLogRecPtr loc)
if (ConfigReloadPending)
{
ConfigReloadPending = false;
- ProcessConfigFile(PGC_SIGHUP);
+ RereadConfigAndReInitSlotList(&standby_slots);
SyncRepInitConfig();
}
@@ -1787,8 +1837,18 @@ WalSndWaitForWal(XLogRecPtr loc)
if (got_STOPPING)
XLogBackgroundFlush();
+ /*
+ * Update the standby slots that have not yet caught up to the flushed
+ * position. It is good to wait up to RecentFlushPtr and then let it
+ * send the changes to logical subscribers one by one which are
+ * already covered in RecentFlushPtr without needing to wait on every
+ * change for standby confirmation.
+ */
+ if (wait_for_standby)
+ FilterStandbySlots(RecentFlushPtr, &standby_slots);
+
/* Update our idea of the currently flushed position. */
- if (!RecoveryInProgress())
+ else if (!RecoveryInProgress())
RecentFlushPtr = GetFlushRecPtr(NULL);
else
RecentFlushPtr = GetXLogReplayRecPtr(NULL);
@@ -1816,9 +1876,18 @@ WalSndWaitForWal(XLogRecPtr loc)
!waiting_for_ping_response)
WalSndKeepalive(false, InvalidXLogRecPtr);
- /* check whether we're done */
- if (loc <= RecentFlushPtr)
+ if (loc > RecentFlushPtr)
+ wait_event = WAIT_EVENT_WAL_SENDER_WAIT_FOR_WAL;
+ else if (standby_slots)
+ {
+ wait_event = WAIT_EVENT_WAIT_FOR_STANDBY_CONFIRMATION;
+ wait_for_standby = true;
+ }
+ else
+ {
+ /* Already caught up and doesn't need to wait for standby_slots. */
break;
+ }
/* Waiting for new WAL. Since we need to wait, we're now caught up. */
WalSndCaughtUp = true;
@@ -1858,9 +1927,11 @@ WalSndWaitForWal(XLogRecPtr loc)
if (pq_is_send_pending())
wakeEvents |= WL_SOCKET_WRITEABLE;
- WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_WAIT_FOR_WAL);
+ WalSndWait(wakeEvents, sleeptime, wait_event);
}
+ list_free(standby_slots);
+
/* reactivate latch so WalSndLoop knows to continue */
SetLatch(MyLatch);
return RecentFlushPtr;
@@ -2268,6 +2339,7 @@ PhysicalConfirmReceivedLocation(XLogRecPtr lsn)
{
ReplicationSlotMarkDirty();
ReplicationSlotsComputeRequiredLSN();
+ PhysicalWakeupLogicalWalSnd();
}
/*
@@ -3530,6 +3602,7 @@ WalSndShmemInit(void)
ConditionVariableInit(&WalSndCtl->wal_flush_cv);
ConditionVariableInit(&WalSndCtl->wal_replay_cv);
+ ConditionVariableInit(&WalSndCtl->wal_confirm_rcv_cv);
}
}
@@ -3599,8 +3672,14 @@ WalSndWait(uint32 socket_events, long timeout, uint32 wait_event)
*
* And, we use separate shared memory CVs for physical and logical
* walsenders for selective wake ups, see WalSndWakeup() for more details.
+ *
+ * If the wait event is WAIT_FOR_STANDBY_CONFIRMATION, wait on another CV
+ * until awakened by physical walsenders after the walreceiver confirms the
+ * receipt of the LSN.
*/
- if (MyWalSnd->kind == REPLICATION_KIND_PHYSICAL)
+ if (wait_event == WAIT_EVENT_WAIT_FOR_STANDBY_CONFIRMATION)
+ ConditionVariablePrepareToSleep(&WalSndCtl->wal_confirm_rcv_cv);
+ else if (MyWalSnd->kind == REPLICATION_KIND_PHYSICAL)
ConditionVariablePrepareToSleep(&WalSndCtl->wal_flush_cv);
else if (MyWalSnd->kind == REPLICATION_KIND_LOGICAL)
ConditionVariablePrepareToSleep(&WalSndCtl->wal_replay_cv);
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index aee5fe7315..fba9040165 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -78,6 +78,7 @@ GSS_OPEN_SERVER "Waiting to read data from the client while establishing a GSSAP
LIBPQWALRECEIVER_CONNECT "Waiting in WAL receiver to establish connection to remote server."
LIBPQWALRECEIVER_RECEIVE "Waiting in WAL receiver to receive data from remote server."
SSL_OPEN_SERVER "Waiting for SSL while attempting connection."
+WAIT_FOR_STANDBY_CONFIRMATION "Waiting for the WAL to be received by physical standby."
WAL_SENDER_WAIT_FOR_WAL "Waiting for WAL to be flushed in WAL sender process."
WAL_SENDER_WRITE_DATA "Waiting for any activity when processing replies from WAL receiver in WAL sender process."
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index 0f5ec63de1..2ff03879ef 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -4618,6 +4618,20 @@ struct config_string ConfigureNamesString[] =
check_debug_io_direct, assign_debug_io_direct, NULL
},
+ {
+ {"standby_slot_names", PGC_SIGHUP, REPLICATION_PRIMARY,
+ gettext_noop("Lists streaming replication standby server slot "
+ "names that logical WAL sender processes will wait for."),
+ gettext_noop("Decoded changes are sent out to plugins by logical "
+ "WAL sender processes only after specified "
+ "replication slots confirm receiving WAL."),
+ GUC_LIST_INPUT | GUC_LIST_QUOTE
+ },
+ &standby_slot_names,
+ "",
+ check_standby_slot_names, assign_standby_slot_names, NULL
+ },
+
/* End-of-list marker */
{
{NULL, 0, 0, NULL, NULL}, NULL, NULL, NULL, NULL, NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 136be912e6..022a205008 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -334,6 +334,8 @@
# method to choose sync standbys, number of sync standbys,
# and comma-separated list of application_name
# from standby(s); '*' = all
+#standby_slot_names = '' # streaming replication standby server slot names that
+ # logical walsender processes will wait for
# - Standby Servers -
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index b310b809c4..62200fcc31 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -241,6 +241,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot;
/* GUCs */
extern PGDLLIMPORT int max_replication_slots;
+extern PGDLLIMPORT char *standby_slot_names;
/* shmem initialization functions */
extern Size ReplicationSlotsShmemSize(void);
@@ -287,4 +288,10 @@ extern void CheckPointReplicationSlots(bool is_shutdown);
extern void CheckSlotRequirements(void);
extern void CheckSlotPermissions(void);
+extern List *GetStandbySlotList(bool copy);
+extern void WaitForStandbyConfirmation(XLogRecPtr wait_for_lsn);
+extern void FilterStandbySlots(XLogRecPtr wait_for_lsn,
+ List **standby_slots);
+extern void RereadConfigAndReInitSlotList(List **standby_slots);
+
#endif /* SLOT_H */
diff --git a/src/include/replication/walsender.h b/src/include/replication/walsender.h
index 1b58d50b3b..9a42b01f9a 100644
--- a/src/include/replication/walsender.h
+++ b/src/include/replication/walsender.h
@@ -45,6 +45,7 @@ extern void WalSndInitStopping(void);
extern void WalSndWaitStopping(void);
extern void HandleWalSndInitStopping(void);
extern void WalSndRqstFileReload(void);
+extern void PhysicalWakeupLogicalWalSnd(void);
/*
* Remember that we want to wakeup walsenders later
diff --git a/src/include/replication/walsender_private.h b/src/include/replication/walsender_private.h
index 3113e9ea47..0f962b0c72 100644
--- a/src/include/replication/walsender_private.h
+++ b/src/include/replication/walsender_private.h
@@ -113,6 +113,13 @@ typedef struct
ConditionVariable wal_flush_cv;
ConditionVariable wal_replay_cv;
+ /*
+ * Used by physical walsenders holding slots specified in
+ * standby_slot_names to wake up logical walsenders holding
+ * failover-enabled slots when a walreceiver confirms the receipt of LSN.
+ */
+ ConditionVariable wal_confirm_rcv_cv;
+
WalSnd walsnds[FLEXIBLE_ARRAY_MEMBER];
} WalSndCtlData;
diff --git a/src/include/utils/guc_hooks.h b/src/include/utils/guc_hooks.h
index 5300c44f3b..464996b4f0 100644
--- a/src/include/utils/guc_hooks.h
+++ b/src/include/utils/guc_hooks.h
@@ -162,5 +162,8 @@ extern bool check_wal_consistency_checking(char **newval, void **extra,
extern void assign_wal_consistency_checking(const char *newval, void *extra);
extern bool check_wal_segment_size(int *newval, void **extra, GucSource source);
extern void assign_wal_sync_method(int new_wal_sync_method, void *extra);
+extern bool check_standby_slot_names(char **newval, void **extra,
+ GucSource source);
+extern void assign_standby_slot_names(const char *newval, void *extra);
#endif /* GUC_HOOKS_H */
diff --git a/src/test/recovery/meson.build b/src/test/recovery/meson.build
index 88fb0306f5..4152c07318 100644
--- a/src/test/recovery/meson.build
+++ b/src/test/recovery/meson.build
@@ -45,6 +45,7 @@ tests += {
't/037_invalid_database.pl',
't/038_save_logical_slots_shutdown.pl',
't/039_end_of_wal.pl',
+ 't/050_standby_failover_slots_sync.pl',
],
},
}
diff --git a/src/test/recovery/t/006_logical_decoding.pl b/src/test/recovery/t/006_logical_decoding.pl
index 5c7b4ca5e3..85f019774c 100644
--- a/src/test/recovery/t/006_logical_decoding.pl
+++ b/src/test/recovery/t/006_logical_decoding.pl
@@ -172,9 +172,10 @@ is($node_primary->slot('otherdb_slot')->{'slot_name'},
undef, 'logical slot was actually dropped with DB');
# Test logical slot advancing and its durability.
+# Pass failover=true (last-arg), it should not have any impact on advancing.
my $logical_slot = 'logical_slot';
$node_primary->safe_psql('postgres',
- "SELECT pg_create_logical_replication_slot('$logical_slot', 'test_decoding', false);"
+ "SELECT pg_create_logical_replication_slot('$logical_slot', 'test_decoding', false, false, true);"
);
$node_primary->psql(
'postgres', "
diff --git a/src/test/recovery/t/050_standby_failover_slots_sync.pl b/src/test/recovery/t/050_standby_failover_slots_sync.pl
index c55a285ca3..69128e2b4c 100644
--- a/src/test/recovery/t/050_standby_failover_slots_sync.pl
+++ b/src/test/recovery/t/050_standby_failover_slots_sync.pl
@@ -8,21 +8,74 @@ use PostgreSQL::Test::Utils;
use Test::More;
##################################################
-# Test that when a subscription with failover enabled is created, it will alter
-# the failover property of the corresponding slot on the publisher.
+# Test primary disallowing specified logical replication slots getting ahead of
+# specified physical replication slots. It uses the following set up:
+#
+# | ----> standby1 (primary_slot_name = sb1_slot)
+# | ----> standby2 (primary_slot_name = sb2_slot)
+# primary ----- |
+# | ----> subscriber1 (failover = true)
+# | ----> subscriber2 (failover = false)
+#
+# standby_slot_names = 'sb1_slot'
+#
+# Set up is configured in such a way that the logical slot of subscriber1 is
+# enabled failover, thus it will wait for the physical slot of
+# standby1(sb1_slot) to catch up before sending decoded changes to subscriber1.
##################################################
-# Create publisher
-my $publisher = PostgreSQL::Test::Cluster->new('publisher');
-$publisher->init(allows_streaming => 'logical');
-$publisher->start;
+# Create primary
+my $primary = PostgreSQL::Test::Cluster->new('primary');
+$primary->init(allows_streaming => 'logical');
-$publisher->safe_psql(
- 'postgres', qq[
- CREATE TABLE tab_int (a int PRIMARY KEY);
- CREATE PUBLICATION regress_mypub FOR TABLE tab_int;
-]);
+# Configure primary to disallow any logical slots that enabled failover from
+# getting ahead of specified physical replication slot (sb1_slot).
+$primary->append_conf(
+ 'postgresql.conf', qq(
+standby_slot_names = 'sb1_slot'
+));
+$primary->start;
+
+$primary->psql('postgres',
+ q{SELECT pg_create_physical_replication_slot('sb1_slot');});
+$primary->psql('postgres',
+ q{SELECT pg_create_physical_replication_slot('sb2_slot');});
+
+$primary->safe_psql('postgres', "CREATE TABLE tab_int (a int PRIMARY KEY);");
+
+my $backup_name = 'backup';
+$primary->backup($backup_name);
+
+# Create a standby
+my $standby1 = PostgreSQL::Test::Cluster->new('standby1');
+$standby1->init_from_backup(
+ $primary, $backup_name,
+ has_streaming => 1,
+ has_restoring => 1);
+$standby1->append_conf(
+ 'postgresql.conf', qq(
+primary_slot_name = 'sb1_slot'
+));
+$standby1->start;
+$primary->wait_for_replay_catchup($standby1);
+
+# Create another standby
+my $standby2 = PostgreSQL::Test::Cluster->new('standby2');
+$standby2->init_from_backup(
+ $primary, $backup_name,
+ has_streaming => 1,
+ has_restoring => 1);
+$standby2->append_conf(
+ 'postgresql.conf', qq(
+primary_slot_name = 'sb2_slot'
+));
+$standby2->start;
+$primary->wait_for_replay_catchup($standby2);
+# Create a publication on the primary
+my $publisher = $primary;
+$publisher->safe_psql('postgres',
+ "CREATE PUBLICATION regress_mypub FOR TABLE tab_int;");
my $publisher_connstr = $publisher->connstr . ' dbname=postgres';
# Create a subscriber node, wait for sync to complete
@@ -30,56 +83,207 @@ my $subscriber1 = PostgreSQL::Test::Cluster->new('subscriber1');
$subscriber1->init;
$subscriber1->start;
-# Create a slot on the publisher with failover disabled
+# Create a table and a subscription with failover = true
+$subscriber1->safe_psql(
+ 'postgres', qq[
+ CREATE TABLE tab_int (a int PRIMARY KEY);
+ CREATE SUBSCRIPTION regress_mysub1 CONNECTION '$publisher_connstr' PUBLICATION regress_mypub WITH (slot_name = lsub1_slot, failover = true);
+]);
+$subscriber1->wait_for_subscription_sync;
+
+# Create another subscriber node without enabling failover, wait for sync to
+# complete
+my $subscriber2 = PostgreSQL::Test::Cluster->new('subscriber2');
+$subscriber2->init;
+$subscriber2->start;
+$subscriber2->safe_psql(
+ 'postgres', qq[
+ CREATE TABLE tab_int (a int PRIMARY KEY);
+ CREATE SUBSCRIPTION regress_mysub2 CONNECTION '$publisher_connstr' PUBLICATION regress_mypub WITH (slot_name = lsub2_slot);
+]);
+$subscriber2->wait_for_subscription_sync;
+
+# Stop the standby associated with the specified physical replication slot so
+# that the logical replication slot won't receive changes until the standby
+# comes up.
+$standby1->stop;
+
+# Create some data on the primary
+my $primary_row_count = 10;
+$primary->safe_psql('postgres',
+ "INSERT INTO tab_int SELECT generate_series(1, $primary_row_count);");
+
+# Wait for the standby that's up and running gets the data from primary
+$primary->wait_for_replay_catchup($standby2);
+my $result = $standby2->safe_psql('postgres',
+ "SELECT count(*) = $primary_row_count FROM tab_int;");
+is($result, 't', "standby2 gets data from primary");
+
+# Wait for the subscription that's up and running and is not enabled for failover.
+# It gets the data from primary without waiting for any standbys.
+$publisher->wait_for_catchup('regress_mysub2');
+$result = $subscriber2->safe_psql('postgres',
+ "SELECT count(*) = $primary_row_count FROM tab_int;");
+is($result, 't', "subscriber2 gets data from primary");
+
+# The subscription that's up and running and is enabled for failover
+# doesn't get the data from primary and keeps waiting for the
+# standby specified in standby_slot_names.
+$result =
+ $subscriber1->safe_psql('postgres', "SELECT count(*) = 0 FROM tab_int;");
+is($result, 't',
+ "subscriber1 doesn't get data from primary until standby1 acknowledges changes"
+);
+
+# Start the standby specified in standby_slot_names and wait for it to catch
+# up with the primary.
+$standby1->start;
+$primary->wait_for_replay_catchup($standby1);
+$result = $standby1->safe_psql('postgres',
+ "SELECT count(*) = $primary_row_count FROM tab_int;");
+is($result, 't', "standby1 gets data from primary");
+
+# Now that the standby specified in standby_slot_names is up and running,
+# primary must send the decoded changes to subscription enabled for failover
+# While the standby was down, this subscriber didn't receive any data from
+# primary i.e. the primary didn't allow it to go ahead of standby.
+$publisher->wait_for_catchup('regress_mysub1');
+$result = $subscriber1->safe_psql('postgres',
+ "SELECT count(*) = $primary_row_count FROM tab_int;");
+is($result, 't',
+ "subscriber1 gets data from primary after standby1 acknowledges changes");
+
+# Stop the standby associated with the specified physical replication slot so
+# that the logical replication slot won't receive changes until the standby
+# slot's restart_lsn is advanced or the slot is removed from the
+# standby_slot_names list.
+$publisher->safe_psql('postgres', "TRUNCATE tab_int;");
+$publisher->wait_for_catchup('regress_mysub1');
+$standby1->stop;
+
+##################################################
+# Verify that when using pg_logical_slot_get_changes to consume changes from a
+# logical slot with failover enabled, it will also wait for the slots specified
+# in standby_slot_names to catch up.
+##################################################
+
+# Create a logical 'test_decoding' replication slot with failover enabled
$publisher->safe_psql('postgres',
- "SELECT 'init' FROM pg_create_logical_replication_slot('lsub1_slot', 'pgoutput', false, false, false);"
+ "SELECT pg_create_logical_replication_slot('test_slot', 'test_decoding', false, false, true);"
+);
+
+my $back_q = $primary->background_psql('postgres', on_error_stop => 0);
+my $pid = $back_q->query('SELECT pg_backend_pid()');
+
+# Try and get changes from the logical slot with failover enabled.
+my $offset = -s $primary->logfile;
+$back_q->query_until(qr//,
+ "SELECT pg_logical_slot_get_changes('test_slot', NULL, NULL);\n");
+
+# Wait until the primary server logs a warning indicating that it is waiting
+# for the sb1_slot to catch up.
+$primary->wait_for_log(
+ qr/WARNING: ( [A-Z0-9]+:)? replication slot \"sb1_slot\" specified in parameter \"standby_slot_names\" does not have active_pid/,
+ $offset);
+
+ok($primary->safe_psql('postgres', "SELECT pg_cancel_backend($pid)"),
+ "cancelling pg_logical_slot_get_changes command");
+
+$back_q->quit;
+
+$publisher->safe_psql('postgres',
+ "SELECT pg_drop_replication_slot('test_slot');"
+);
+
+##################################################
+# Test that logical replication will wait for the user-created inactive
+# physical slot to catch up until we remove the slot from standby_slot_names.
+##################################################
+
+# Create some data on the primary
+$primary_row_count = 10;
+$primary->safe_psql('postgres',
+ "INSERT INTO tab_int SELECT generate_series(1, $primary_row_count);");
+
+$result =
+ $subscriber1->safe_psql('postgres', "SELECT count(*) = 0 FROM tab_int;");
+is($result, 't',
+ "subscriber1 doesn't get data as the sb1_slot doesn't catch up");
+
+# Remove the standby from the standby_slot_names list and reload the
+# configuration.
+$primary->adjust_conf('postgresql.conf', 'standby_slot_names', "''");
+$primary->reload;
+
+# Since there are no slots in standby_slot_names, the primary server should now
+# send the decoded changes to the subscription.
+$publisher->wait_for_catchup('regress_mysub1');
+$result = $subscriber1->safe_psql('postgres',
+ "SELECT count(*) = $primary_row_count FROM tab_int;");
+is($result, 't',
+ "subscriber1 gets data from primary after standby1 is removed from the standby_slot_names list"
+);
+
+# Put the standby back on the primary_slot_name for the rest of the tests
+$primary->adjust_conf('postgresql.conf', 'standby_slot_names', 'sb1_slot');
+$primary->reload;
+
+##################################################
+# Test that when a subscription with failover enabled is created, it will alter
+# the failover property of the corresponding slot on the publisher.
+##################################################
+
+# Create a slot on the publisher with failover disabled
+$primary->safe_psql('postgres',
+ "SELECT 'init' FROM pg_create_logical_replication_slot('lsub3_slot', 'pgoutput', false, false, false);"
);
# Confirm that the failover flag on the slot is turned off
-is( $publisher->safe_psql(
+is( $primary->safe_psql(
'postgres',
- q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub3_slot';}
),
"f",
- 'logical slot has failover false on the publisher');
+ 'logical slot has failover false on the primary');
# Create another subscription (using the same slot created above) that enables
# failover.
-$subscriber1->safe_psql(
- 'postgres', qq[
- CREATE TABLE tab_int (a int PRIMARY KEY);
- CREATE SUBSCRIPTION regress_mysub1 CONNECTION '$publisher_connstr' PUBLICATION regress_mypub WITH (slot_name = lsub1_slot, copy_data=false, failover = true, create_slot = false);
-]);
+$subscriber1->safe_psql('postgres',
+ "CREATE SUBSCRIPTION regress_mysub3 CONNECTION '$publisher_connstr' "
+ . "PUBLICATION regress_mypub WITH (slot_name = lsub3_slot, copy_data=false, failover = true, create_slot = false);"
+);
# Confirm that the failover flag on the slot has now been turned on
-is( $publisher->safe_psql(
+is( $primary->safe_psql(
'postgres',
- q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub3_slot';}
),
"t",
- 'logical slot has failover true on the publisher');
+ 'logical slot has failover true on the primary');
+
+$primary->safe_psql('postgres', "TRUNCATE tab_int");
##################################################
# Test if changing the failover property of a subscription updates the
# corresponding failover property of the slot.
##################################################
-$subscriber1->safe_psql('postgres', "ALTER SUBSCRIPTION regress_mysub1 DISABLE");
+$subscriber1->safe_psql('postgres', "ALTER SUBSCRIPTION regress_mysub3 DISABLE");
# Wait for the replication slot to become inactive on the publisher
-$publisher->poll_query_until(
+$primary->poll_query_until(
'postgres',
- "SELECT COUNT(*) FROM pg_catalog.pg_replication_slots WHERE slot_name = 'lsub1_slot' AND active='f'",
+ "SELECT COUNT(*) FROM pg_catalog.pg_replication_slots WHERE slot_name = 'lsub3_slot' AND active='f'",
1);
# Disable failover
$subscriber1->safe_psql('postgres',
- "ALTER SUBSCRIPTION regress_mysub1 SET (failover = false)");
+ "ALTER SUBSCRIPTION regress_mysub3 SET (failover = false)");
# Confirm that the failover flag on the slot has now been turned off
-is( $publisher->safe_psql(
+is( $primary->safe_psql(
'postgres',
- q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub3_slot';}
),
"f",
'logical slot has failover false on the publisher');
@@ -87,16 +291,18 @@ is( $publisher->safe_psql(
# Enable failover and the subscription
$subscriber1->safe_psql(
'postgres', qq[
- ALTER SUBSCRIPTION regress_mysub1 SET (failover = true);
- ALTER SUBSCRIPTION regress_mysub1 ENABLE;
+ ALTER SUBSCRIPTION regress_mysub3 SET (failover = true);
+ ALTER SUBSCRIPTION regress_mysub3 ENABLE;
]);
# Confirm that the failover flag on the slot has now been turned on
-ok( $publisher->poll_query_until(
+ok( $primary->poll_query_until(
'postgres',
- "SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';"),
+ "SELECT failover from pg_replication_slots WHERE slot_name = 'lsub3_slot';"),
'logical slot has failover true on the publisher');
+$subscriber1->safe_psql('postgres', "DROP SUBSCRIPTION regress_mysub3");
+
##################################################
# Test logical failover slots on the standby
# Configure standby1 to replicate and synchronize logical slots configured
@@ -108,34 +314,27 @@ ok( $publisher->poll_query_until(
# | lsub1_slot(synced_slot)
##################################################
-my $primary = $publisher;
-my $backup_name = 'backup';
-$primary->backup($backup_name);
-
-# Create a standby
-my $standby1 = PostgreSQL::Test::Cluster->new('standby1');
-$standby1->init_from_backup(
- $primary, $backup_name,
- has_streaming => 1,
- has_restoring => 1);
-
my $connstr_1 = $primary->connstr;
$standby1->append_conf(
- 'postgresql.conf', qq(
+ 'postgresql.conf', qq(
enable_syncslot = true
hot_standby_feedback = on
primary_slot_name = 'sb1_slot'
primary_conninfo = '$connstr_1 dbname=postgres'
));
-$primary->psql('postgres',
- q{SELECT pg_create_physical_replication_slot('sb1_slot');});
+# Add this standby into the primary's configuration
+$primary->append_conf(
+ 'postgresql.conf', qq(
+standby_slot_names = 'sb1_slot'
+));
+$primary->reload;
my $standby1_conninfo = $standby1->connstr . ' dbname=postgres';
# Wait for the standby to start sync
-my $offset = -s $standby1->logfile;
-$standby1->start;
+$offset = -s $standby1->logfile;
+$standby1->restart;
$standby1->wait_for_log(
qr/LOG: ( [A-Z0-9]+:)? waiting for remote slot \"lsub1_slot\"/,
$offset);
@@ -210,7 +409,7 @@ $standby1->safe_psql('postgres', 'ALTER SYSTEM SET hot_standby_feedback = off;')
$standby1->restart;
# Attempting to perform logical decoding on a synced slot should result in an error
-my ($result, $stdout, $stderr) = $standby1->psql('postgres',
+my ($result1, $stdout, $stderr) = $standby1->psql('postgres',
"select * from pg_logical_slot_get_changes('lsub1_slot',NULL,NULL);");
ok($stderr =~ /ERROR: cannot use replication slot "lsub1_slot" for logical decoding/,
"logical decoding is not allowed on synced slot");
@@ -224,7 +423,7 @@ ok($stderr =~ /ERROR: cannot alter replication slot "lsub1_slot"/,
"synced slot on standby cannot be altered");
# Attempting to drop a synced slot should result in an error
-($result, $stdout, $stderr) = $standby1->psql('postgres',
+($result1, $stdout, $stderr) = $standby1->psql('postgres',
"SELECT pg_drop_replication_slot('lsub1_slot');");
ok($stderr =~ /ERROR: cannot drop replication slot "lsub1_slot"/,
"synced slot on standby cannot be dropped");
--
2.34.1
[application/octet-stream] v57-0001-Enable-setting-failover-property-for-a-slot-thro.patch (117.7K, ../CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com/4-v57-0001-Enable-setting-failover-property-for-a-slot-thro.patch)
download | inline diff:
From 3bac957704991b1add1c457d5d5c98cd8353cf5c Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Thu, 4 Jan 2024 09:15:26 +0530
Subject: [PATCH v57 1/4] Enable setting failover property for a slot through
SQL API and subscription commands
This commit adds the failover property to the replication slot. The
failover property indicates whether the slot will be synced to the standby
servers, enabling the resumption of corresponding logical replication
after failover. But note that this commit does not yet include the
capability to actually sync the replication slot; the next patch will
address that.
In addition, a new replication command named ALTER_REPLICATION_SLOT and a
corresponding walreceiver API function named walrcv_alter_slot have been
implemented. These additions provide subscribers or users the ability to
modify the failover property of a replication slot on the publisher.
Moreover, a new subscription option called 'failover' has been added,
allowing users to set it when creating or altering a subscription. Also,
a new parameter 'failover' is added to the
pg_create_logical_replication_slot function.
The value of the 'failover' flag is displayed as part of
pg_replication_slots view.
---
contrib/test_decoding/expected/slot.out | 58 +++++
contrib/test_decoding/sql/slot.sql | 13 ++
doc/src/sgml/catalogs.sgml | 12 ++
doc/src/sgml/func.sgml | 11 +-
doc/src/sgml/protocol.sgml | 51 +++++
doc/src/sgml/ref/alter_subscription.sgml | 28 ++-
doc/src/sgml/ref/create_subscription.sgml | 25 +++
doc/src/sgml/system-views.sgml | 11 +
src/backend/catalog/pg_subscription.c | 1 +
src/backend/catalog/system_functions.sql | 1 +
src/backend/catalog/system_views.sql | 6 +-
src/backend/commands/subscriptioncmds.c | 202 ++++++++++++++++--
.../libpqwalreceiver/libpqwalreceiver.c | 38 +++-
src/backend/replication/logical/tablesync.c | 53 +++--
src/backend/replication/logical/worker.c | 67 +++++-
src/backend/replication/repl_gram.y | 20 +-
src/backend/replication/repl_scanner.l | 2 +
src/backend/replication/slot.c | 33 ++-
src/backend/replication/slotfuncs.c | 16 +-
src/backend/replication/walreceiver.c | 2 +-
src/backend/replication/walsender.c | 67 +++++-
src/bin/pg_dump/pg_dump.c | 20 +-
src/bin/pg_dump/pg_dump.h | 1 +
src/bin/pg_upgrade/info.c | 5 +-
src/bin/pg_upgrade/pg_upgrade.c | 6 +-
src/bin/pg_upgrade/pg_upgrade.h | 2 +
src/bin/pg_upgrade/t/003_logical_slots.pl | 6 +-
src/bin/psql/describe.c | 8 +-
src/bin/psql/tab-complete.c | 2 +-
src/include/catalog/pg_proc.dat | 14 +-
src/include/catalog/pg_subscription.h | 11 +
src/include/nodes/replnodes.h | 12 ++
src/include/replication/slot.h | 9 +-
src/include/replication/walreceiver.h | 18 +-
src/include/replication/worker_internal.h | 3 +-
.../t/050_standby_failover_slots_sync.pl | 102 +++++++++
src/test/regress/expected/rules.out | 5 +-
src/test/regress/expected/subscription.out | 165 +++++++-------
src/test/regress/sql/subscription.sql | 8 +
src/tools/pgindent/typedefs.list | 2 +
40 files changed, 960 insertions(+), 156 deletions(-)
create mode 100644 src/test/recovery/t/050_standby_failover_slots_sync.pl
diff --git a/contrib/test_decoding/expected/slot.out b/contrib/test_decoding/expected/slot.out
index 63a9940f73..261d8886d3 100644
--- a/contrib/test_decoding/expected/slot.out
+++ b/contrib/test_decoding/expected/slot.out
@@ -406,3 +406,61 @@ SELECT pg_drop_replication_slot('copied_slot2_notemp');
(1 row)
+-- Test failover option of slots.
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_true_slot', 'test_decoding', false, false, true);
+ ?column?
+----------
+ init
+(1 row)
+
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_false_slot', 'test_decoding', false, false, false);
+ ?column?
+----------
+ init
+(1 row)
+
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_default_slot', 'test_decoding', false, false);
+ ?column?
+----------
+ init
+(1 row)
+
+SELECT 'init' FROM pg_create_physical_replication_slot('physical_slot');
+ ?column?
+----------
+ init
+(1 row)
+
+SELECT slot_name, slot_type, failover FROM pg_replication_slots;
+ slot_name | slot_type | failover
+-----------------------+-----------+----------
+ failover_true_slot | logical | t
+ failover_false_slot | logical | f
+ failover_default_slot | logical | f
+ physical_slot | physical | f
+(4 rows)
+
+SELECT pg_drop_replication_slot('failover_true_slot');
+ pg_drop_replication_slot
+--------------------------
+
+(1 row)
+
+SELECT pg_drop_replication_slot('failover_false_slot');
+ pg_drop_replication_slot
+--------------------------
+
+(1 row)
+
+SELECT pg_drop_replication_slot('failover_default_slot');
+ pg_drop_replication_slot
+--------------------------
+
+(1 row)
+
+SELECT pg_drop_replication_slot('physical_slot');
+ pg_drop_replication_slot
+--------------------------
+
+(1 row)
+
diff --git a/contrib/test_decoding/sql/slot.sql b/contrib/test_decoding/sql/slot.sql
index 1aa27c5667..45aeae7fd5 100644
--- a/contrib/test_decoding/sql/slot.sql
+++ b/contrib/test_decoding/sql/slot.sql
@@ -176,3 +176,16 @@ ORDER BY o.slot_name, c.slot_name;
SELECT pg_drop_replication_slot('orig_slot2');
SELECT pg_drop_replication_slot('copied_slot2_no_change');
SELECT pg_drop_replication_slot('copied_slot2_notemp');
+
+-- Test failover option of slots.
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_true_slot', 'test_decoding', false, false, true);
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_false_slot', 'test_decoding', false, false, false);
+SELECT 'init' FROM pg_create_logical_replication_slot('failover_default_slot', 'test_decoding', false, false);
+SELECT 'init' FROM pg_create_physical_replication_slot('physical_slot');
+
+SELECT slot_name, slot_type, failover FROM pg_replication_slots;
+
+SELECT pg_drop_replication_slot('failover_true_slot');
+SELECT pg_drop_replication_slot('failover_false_slot');
+SELECT pg_drop_replication_slot('failover_default_slot');
+SELECT pg_drop_replication_slot('physical_slot');
diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml
index 3ec7391ec5..e666730c64 100644
--- a/doc/src/sgml/catalogs.sgml
+++ b/doc/src/sgml/catalogs.sgml
@@ -7990,6 +7990,18 @@ SCRAM-SHA-256$<replaceable><iteration count></replaceable>:<replaceable>&l
</para></entry>
</row>
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>subfailoverstate</structfield> <type>char</type>
+ </para>
+ <para>
+ State codes for failover mode:
+ <literal>d</literal> = disabled,
+ <literal>p</literal> = pending enablement,
+ <literal>e</literal> = enabled
+ </para></entry>
+ </row>
+
<row>
<entry role="catalog_table_entry"><para role="column_definition">
<structfield>subconninfo</structfield> <type>text</type>
diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index cec21e42c0..169dba1a9d 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -27547,7 +27547,7 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset
<indexterm>
<primary>pg_create_logical_replication_slot</primary>
</indexterm>
- <function>pg_create_logical_replication_slot</function> ( <parameter>slot_name</parameter> <type>name</type>, <parameter>plugin</parameter> <type>name</type> <optional>, <parameter>temporary</parameter> <type>boolean</type>, <parameter>twophase</parameter> <type>boolean</type> </optional> )
+ <function>pg_create_logical_replication_slot</function> ( <parameter>slot_name</parameter> <type>name</type>, <parameter>plugin</parameter> <type>name</type> <optional>, <parameter>temporary</parameter> <type>boolean</type>, <parameter>twophase</parameter> <type>boolean</type>, <parameter>failover</parameter> <type>boolean</type> </optional> )
<returnvalue>record</returnvalue>
( <parameter>slot_name</parameter> <type>name</type>,
<parameter>lsn</parameter> <type>pg_lsn</type> )
@@ -27562,8 +27562,13 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset
released upon any error. The optional fourth parameter,
<parameter>twophase</parameter>, when set to true, specifies
that the decoding of prepared transactions is enabled for this
- slot. A call to this function has the same effect as the replication
- protocol command <literal>CREATE_REPLICATION_SLOT ... LOGICAL</literal>.
+ slot. The optional fifth parameter,
+ <parameter>failover</parameter>, when set to true,
+ specifies that this slot is enabled to be synced to the
+ physical standbys so that logical replication can be resumed
+ after failover. A call to this function has the same effect as
+ the replication protocol command
+ <literal>CREATE_REPLICATION_SLOT ... LOGICAL</literal>.
</para></entry>
</row>
diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml
index 6c3e8a631d..9dc7b0175b 100644
--- a/doc/src/sgml/protocol.sgml
+++ b/doc/src/sgml/protocol.sgml
@@ -2060,6 +2060,16 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;"
</para>
</listitem>
</varlistentry>
+
+ <varlistentry>
+ <term><literal>FAILOVER [ <replaceable class="parameter">boolean</replaceable> ]</literal></term>
+ <listitem>
+ <para>
+ If true, the slot is enabled to be synced to the physical
+ standbys so that logical replication can be resumed after failover.
+ </para>
+ </listitem>
+ </varlistentry>
</variablelist>
<para>
@@ -2124,6 +2134,47 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;"
</listitem>
</varlistentry>
+ <varlistentry id="protocol-replication-alter-replication-slot" xreflabel="ALTER_REPLICATION_SLOT">
+ <term><literal>ALTER_REPLICATION_SLOT</literal> <replaceable class="parameter">slot_name</replaceable> ( <replaceable class="parameter">option</replaceable> [, ...] )
+ <indexterm><primary>ALTER_REPLICATION_SLOT</primary></indexterm>
+ </term>
+ <listitem>
+ <para>
+ Change the definition of a replication slot.
+ See <xref linkend="streaming-replication-slots"/> for more about
+ replication slots. This command is currently only supported for logical
+ replication slots.
+ </para>
+
+ <variablelist>
+ <varlistentry>
+ <term><replaceable class="parameter">slot_name</replaceable></term>
+ <listitem>
+ <para>
+ The name of the slot to alter. Must be a valid replication slot
+ name (see <xref linkend="streaming-replication-slots-manipulation"/>).
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+
+ <para>The following options are supported:</para>
+
+ <variablelist>
+ <varlistentry>
+ <term><literal>FAILOVER [ <replaceable class="parameter">boolean</replaceable> ]</literal></term>
+ <listitem>
+ <para>
+ If true, the slot is enabled to be synced to the physical
+ standbys so that logical replication can be resumed after failover.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+
+ </listitem>
+ </varlistentry>
+
<varlistentry id="protocol-replication-read-replication-slot">
<term><literal>READ_REPLICATION_SLOT</literal> <replaceable class="parameter">slot_name</replaceable>
<indexterm><primary>READ_REPLICATION_SLOT</primary></indexterm>
diff --git a/doc/src/sgml/ref/alter_subscription.sgml b/doc/src/sgml/ref/alter_subscription.sgml
index 6d36ff0dc9..e4e1b14ebc 100644
--- a/doc/src/sgml/ref/alter_subscription.sgml
+++ b/doc/src/sgml/ref/alter_subscription.sgml
@@ -73,11 +73,17 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
These commands also cannot be executed when the subscription has
<link linkend="sql-createsubscription-params-with-two-phase"><literal>two_phase</literal></link>
- commit enabled, unless
+ commit enabled or
+ <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>
+ enabled, unless
<link linkend="sql-createsubscription-params-with-copy-data"><literal>copy_data</literal></link>
is <literal>false</literal>. See column <structfield>subtwophasestate</structfield>
- of <link linkend="catalog-pg-subscription"><structname>pg_subscription</structname></link>
- to know the actual two-phase state.
+ and <structfield>subfailoverstate</structfield> of
+ <link linkend="catalog-pg-subscription"><structname>pg_subscription</structname></link>
+ to know the actual state.
+
+ If <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>
+ is enabled, you can temporarily disable it in order to execute these commands.
</para>
</refsect1>
@@ -226,10 +232,22 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
<link linkend="sql-createsubscription-params-with-streaming"><literal>streaming</literal></link>,
<link linkend="sql-createsubscription-params-with-disable-on-error"><literal>disable_on_error</literal></link>,
<link linkend="sql-createsubscription-params-with-password-required"><literal>password_required</literal></link>,
- <link linkend="sql-createsubscription-params-with-run-as-owner"><literal>run_as_owner</literal></link>, and
- <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>.
+ <link linkend="sql-createsubscription-params-with-run-as-owner"><literal>run_as_owner</literal></link>,
+ <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>, and
+ <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>.
Only a superuser can set <literal>password_required = false</literal>.
</para>
+
+ <para>
+ When altering the
+ <link linkend="sql-createsubscription-params-with-slot-name"><literal>slot_name</literal></link>,
+ the <literal>failover</literal> property of the new slot may differ from the
+ <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>
+ parameter specified in the subscription. When creating the slot,
+ ensure the slot failover property matches the
+ <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>
+ parameter value of the subscription.
+ </para>
</listitem>
</varlistentry>
diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index f1c20b3a46..4d17e93a09 100644
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -399,6 +399,31 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
</para>
</listitem>
</varlistentry>
+
+ <varlistentry id="sql-createsubscription-params-with-failover">
+ <term><literal>failover</literal> (<type>boolean</type>)</term>
+ <listitem>
+ <para>
+ Specifies whether the replication slot associated with the subscription
+ is enabled to be synced to the physical standbys so that logical
+ replication can be resumed from the new primary after failover.
+ The default is <literal>false</literal>.
+ </para>
+
+ <para>
+ The implementation of failover requires that replication
+ has successfully finished the initial table synchronization
+ phase. So even when <literal>failover</literal> is enabled for a
+ subscription, the internal failover state remains
+ temporarily <quote>pending</quote> until the initialization phase
+ completes. See column <structfield>subfailoverstate</structfield>
+ of <link linkend="catalog-pg-subscription"><structname>pg_subscription</structname></link>
+ to know the actual failover state. It is the user's responsibility
+ to ensure that the initial table synchronization has been completed
+ before allowing the subscription to transition to the new primary.
+ </para>
+ </listitem>
+ </varlistentry>
</variablelist></para>
</listitem>
diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml
index 72d01fc624..c10880b200 100644
--- a/doc/src/sgml/system-views.sgml
+++ b/doc/src/sgml/system-views.sgml
@@ -2555,6 +2555,17 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx
</itemizedlist>
</para></entry>
</row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>failover</structfield> <type>bool</type>
+ </para>
+ <para>
+ True if this logical slot is enabled to be synced to the physical
+ standbys so that logical replication can be resumed from the new primary
+ after failover. Always false for physical slots.
+ </para></entry>
+ </row>
</tbody>
</tgroup>
</table>
diff --git a/src/backend/catalog/pg_subscription.c b/src/backend/catalog/pg_subscription.c
index c516c25ac7..53cda8c6d6 100644
--- a/src/backend/catalog/pg_subscription.c
+++ b/src/backend/catalog/pg_subscription.c
@@ -73,6 +73,7 @@ GetSubscription(Oid subid, bool missing_ok)
sub->disableonerr = subform->subdisableonerr;
sub->passwordrequired = subform->subpasswordrequired;
sub->runasowner = subform->subrunasowner;
+ sub->failoverstate = subform->subfailoverstate;
/* Get conninfo */
datum = SysCacheGetAttrNotNull(SUBSCRIPTIONOID,
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index f315fecf18..346cfb98a0 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -479,6 +479,7 @@ CREATE OR REPLACE FUNCTION pg_create_logical_replication_slot(
IN slot_name name, IN plugin name,
IN temporary boolean DEFAULT false,
IN twophase boolean DEFAULT false,
+ IN failover boolean DEFAULT false,
OUT slot_name name, OUT lsn pg_lsn)
RETURNS RECORD
LANGUAGE INTERNAL
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index e43e36f5ac..1e954147e5 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1023,7 +1023,8 @@ CREATE VIEW pg_replication_slots AS
L.wal_status,
L.safe_wal_size,
L.two_phase,
- L.conflict_reason
+ L.conflict_reason,
+ L.failover
FROM pg_get_replication_slots() AS L
LEFT JOIN pg_database D ON (L.datoid = D.oid);
@@ -1357,7 +1358,8 @@ REVOKE ALL ON pg_subscription FROM public;
GRANT SELECT (oid, subdbid, subskiplsn, subname, subowner, subenabled,
subbinary, substream, subtwophasestate, subdisableonerr,
subpasswordrequired, subrunasowner,
- subslotname, subsynccommit, subpublications, suborigin)
+ subslotname, subsynccommit, subpublications, suborigin,
+ subfailoverstate)
ON pg_subscription TO public;
CREATE VIEW pg_stat_subscription_stats AS
diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index 75e6cd8ae3..c76898d3ae 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -71,6 +71,7 @@
#define SUBOPT_RUN_AS_OWNER 0x00001000
#define SUBOPT_LSN 0x00002000
#define SUBOPT_ORIGIN 0x00004000
+#define SUBOPT_FAILOVER 0x00008000
/* check if the 'val' has 'bits' set */
#define IsSet(val, bits) (((val) & (bits)) == (bits))
@@ -96,6 +97,7 @@ typedef struct SubOpts
bool passwordrequired;
bool runasowner;
char *origin;
+ bool failover;
XLogRecPtr lsn;
} SubOpts;
@@ -157,6 +159,8 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
opts->runasowner = false;
if (IsSet(supported_opts, SUBOPT_ORIGIN))
opts->origin = pstrdup(LOGICALREP_ORIGIN_ANY);
+ if (IsSet(supported_opts, SUBOPT_FAILOVER))
+ opts->failover = false;
/* Parse options */
foreach(lc, stmt_options)
@@ -326,6 +330,15 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("unrecognized origin value: \"%s\"", opts->origin));
}
+ else if (IsSet(supported_opts, SUBOPT_FAILOVER) &&
+ strcmp(defel->defname, "failover") == 0)
+ {
+ if (IsSet(opts->specified_opts, SUBOPT_FAILOVER))
+ errorConflictingDefElem(defel, pstate);
+
+ opts->specified_opts |= SUBOPT_FAILOVER;
+ opts->failover = defGetBoolean(defel);
+ }
else if (IsSet(supported_opts, SUBOPT_LSN) &&
strcmp(defel->defname, "lsn") == 0)
{
@@ -591,7 +604,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
SUBOPT_SYNCHRONOUS_COMMIT | SUBOPT_BINARY |
SUBOPT_STREAMING | SUBOPT_TWOPHASE_COMMIT |
SUBOPT_DISABLE_ON_ERR | SUBOPT_PASSWORD_REQUIRED |
- SUBOPT_RUN_AS_OWNER | SUBOPT_ORIGIN);
+ SUBOPT_RUN_AS_OWNER | SUBOPT_ORIGIN |
+ SUBOPT_FAILOVER);
parse_subscription_options(pstate, stmt->options, supported_opts, &opts);
/*
@@ -710,6 +724,10 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
publicationListToArray(publications);
values[Anum_pg_subscription_suborigin - 1] =
CStringGetTextDatum(opts.origin);
+ values[Anum_pg_subscription_subfailoverstate - 1] =
+ CharGetDatum(opts.failover ?
+ LOGICALREP_FAILOVER_STATE_PENDING :
+ LOGICALREP_FAILOVER_STATE_DISABLED);
tup = heap_form_tuple(RelationGetDescr(rel), values, nulls);
@@ -746,6 +764,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
PG_TRY();
{
+ bool failover_enabled = false;
+
check_publications(wrconn, publications);
check_publications_origin(wrconn, publications, opts.copy_data,
opts.origin, NULL, 0, stmt->subname);
@@ -776,6 +796,19 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
InvalidXLogRecPtr, true);
}
+ /*
+ * Even if failover is set, don't create the slot with failover
+ * enabled. Will enable it once all the tables are synced and
+ * ready. The intention is that if failover happens at the time of
+ * table-sync, user should re-launch the subscription instead of
+ * relying on main slot (if synced) with no table-sync data
+ * present. When the subscription has no tables, leave failover as
+ * false to allow ALTER SUBSCRIPTION ... REFRESH PUBLICATION to
+ * work.
+ */
+ if (opts.failover && !opts.copy_data && tables != NIL)
+ failover_enabled = true;
+
/*
* If requested, create permanent slot for the subscription. We
* won't use the initial snapshot for anything, so no need to
@@ -807,15 +840,38 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
twophase_enabled = true;
walrcv_create_slot(wrconn, opts.slot_name, false, twophase_enabled,
- CRS_NOEXPORT_SNAPSHOT, NULL);
-
- if (twophase_enabled)
- UpdateTwoPhaseState(subid, LOGICALREP_TWOPHASE_STATE_ENABLED);
+ failover_enabled, CRS_NOEXPORT_SNAPSHOT, NULL);
+ /* Update twophase and/or failover state */
+ EnableTwoPhaseFailoverTriState(subid, twophase_enabled,
+ failover_enabled);
ereport(NOTICE,
(errmsg("created replication slot \"%s\" on publisher",
opts.slot_name)));
}
+
+ /*
+ * If the slot_name is specified without the create_slot option,
+ * it is possible that the user intends to use an existing slot on
+ * the publisher, so here we alter the failover property of the
+ * slot to match the failover value in subscription.
+ *
+ * We do not need to change the failover to false if the server
+ * does not support failover (e.g. pre-PG17).
+ */
+ else if (opts.slot_name &&
+ (failover_enabled || walrcv_server_version(wrconn) >= 170000))
+ {
+ bool failover_delayed = (!failover_enabled && opts.failover);
+
+ walrcv_alter_slot(wrconn, opts.slot_name, failover_enabled);
+ ereport(NOTICE,
+ (errmsg("changed the failover state of replication slot \"%s\" on publisher to %s",
+ opts.slot_name, failover_enabled ? "true" : "false"),
+ failover_delayed ?
+ errdetail("The failover state will be set to true once table synchronization has been completed.")
+ : 0));
+ }
}
PG_FINALLY();
{
@@ -1079,6 +1135,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
HeapTuple tup;
Oid subid;
bool update_tuple = false;
+ bool set_failover = false;
Subscription *sub;
Form_pg_subscription form;
bits32 supported_opts;
@@ -1132,7 +1189,8 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
SUBOPT_SYNCHRONOUS_COMMIT | SUBOPT_BINARY |
SUBOPT_STREAMING | SUBOPT_DISABLE_ON_ERR |
SUBOPT_PASSWORD_REQUIRED |
- SUBOPT_RUN_AS_OWNER | SUBOPT_ORIGIN);
+ SUBOPT_RUN_AS_OWNER | SUBOPT_ORIGIN |
+ SUBOPT_FAILOVER);
parse_subscription_options(pstate, stmt->options,
supported_opts, &opts);
@@ -1218,6 +1276,47 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
replaces[Anum_pg_subscription_suborigin - 1] = true;
}
+ if (IsSet(opts.specified_opts, SUBOPT_FAILOVER))
+ {
+ if (!sub->slotname)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot set failover for subscription that does not have slot name")));
+
+ /*
+ * Do not allow changing the failover state to false if the
+ * subscription is enabled. This is because the failover
+ * state of the slot on the publisher cannot be modified if
+ * the slot is currently being acquired by the apply
+ * worker.
+ */
+ if (!opts.failover && sub->enabled)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot set %s for enabled subscription",
+ "failover = false")));
+
+ /*
+ * If opts.failover is true, we don't change the failover
+ * state to ENABLED immediately because it's possible that
+ * some tables haven't reached the READY state yet.
+ * Instead, we set the failover state to PENDING and let it
+ * be handled by the apply worker.
+ */
+ values[Anum_pg_subscription_subfailoverstate - 1] =
+ CharGetDatum(opts.failover ?
+ LOGICALREP_FAILOVER_STATE_PENDING:
+ LOGICALREP_FAILOVER_STATE_DISABLED);
+ replaces[Anum_pg_subscription_subfailoverstate - 1] = true;
+
+ /*
+ * If opts.failover is false, the failover state of the
+ * slot should be changed after the catalog update is
+ * completed.
+ */
+ set_failover = !opts.failover;
+ }
+
update_tuple = true;
break;
}
@@ -1279,13 +1378,22 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
errhint("Use ALTER SUBSCRIPTION ... SET PUBLICATION ... WITH (refresh = false).")));
/*
- * See ALTER_SUBSCRIPTION_REFRESH for details why this is
- * not allowed.
+ * See ALTER_SUBSCRIPTION_REFRESH for details why
+ * copy_data is not allowed when twophase or failover is
+ * enabled.
*/
if (sub->twophasestate == LOGICALREP_TWOPHASE_STATE_ENABLED && opts.copy_data)
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
- errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when two_phase is enabled"),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when %s is enabled", "two_phase"),
+ errhint("Use ALTER SUBSCRIPTION ... SET PUBLICATION with refresh = false, or with copy_data = false, or use DROP/CREATE SUBSCRIPTION.")));
+
+ if (sub->failoverstate == LOGICALREP_FAILOVER_STATE_ENABLED && opts.copy_data)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when %s is enabled", "failover"),
errhint("Use ALTER SUBSCRIPTION ... SET PUBLICATION with refresh = false, or with copy_data = false, or use DROP/CREATE SUBSCRIPTION.")));
PreventInTransactionBlock(isTopLevel, "ALTER SUBSCRIPTION with refresh");
@@ -1334,13 +1442,26 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
"ALTER SUBSCRIPTION ... DROP PUBLICATION ... WITH (refresh = false)")));
/*
- * See ALTER_SUBSCRIPTION_REFRESH for details why this is
- * not allowed.
+ * See ALTER_SUBSCRIPTION_REFRESH for details why
+ * copy_data is not allowed when twophase or failover is
+ * enabled.
*/
if (sub->twophasestate == LOGICALREP_TWOPHASE_STATE_ENABLED && opts.copy_data)
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
- errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when two_phase is enabled"),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when %s is enabled", "two_phase"),
+ /* translator: %s is an SQL ALTER command */
+ errhint("Use %s with refresh = false, or with copy_data = false, or use DROP/CREATE SUBSCRIPTION.",
+ isadd ?
+ "ALTER SUBSCRIPTION ... ADD PUBLICATION" :
+ "ALTER SUBSCRIPTION ... DROP PUBLICATION")));
+
+ if (sub->failoverstate == LOGICALREP_FAILOVER_STATE_ENABLED && opts.copy_data)
+ ereport(ERROR,
+ (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION with refresh and copy_data is not allowed when %s is enabled", "failover"),
/* translator: %s is an SQL ALTER command */
errhint("Use %s with refresh = false, or with copy_data = false, or use DROP/CREATE SUBSCRIPTION.",
isadd ?
@@ -1389,7 +1510,19 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
if (sub->twophasestate == LOGICALREP_TWOPHASE_STATE_ENABLED && opts.copy_data)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
- errmsg("ALTER SUBSCRIPTION ... REFRESH with copy_data is not allowed when two_phase is enabled"),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION ... REFRESH with copy_data is not allowed when %s is enabled", "two_phase"),
+ errhint("Use ALTER SUBSCRIPTION ... REFRESH with copy_data = false, or use DROP/CREATE SUBSCRIPTION.")));
+
+ /*
+ * See comments above for twophasestate, same holds true for
+ * 'failover'.
+ */
+ if (sub->failoverstate == LOGICALREP_FAILOVER_STATE_ENABLED && opts.copy_data)
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ /* translator: %s is a subscription option */
+ errmsg("ALTER SUBSCRIPTION ... REFRESH with copy_data is not allowed when %s is enabled", "failover"),
errhint("Use ALTER SUBSCRIPTION ... REFRESH with copy_data = false, or use DROP/CREATE SUBSCRIPTION.")));
PreventInTransactionBlock(isTopLevel, "ALTER SUBSCRIPTION ... REFRESH");
@@ -1453,6 +1586,49 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
heap_freetuple(tup);
}
+ /*
+ * Try to acquire the connection necessary for altering slot.
+ *
+ * The slot will be altered here only if setting the failover flag to
+ * false in the slot.
+ *
+ * This has to be at the end because otherwise if there is an error
+ * while doing the database operations we won't be able to rollback
+ * altered slot.
+ */
+ if (set_failover)
+ {
+ bool must_use_password;
+ char *err;
+ WalReceiverConn *wrconn;
+
+ /* Load the library providing us libpq calls. */
+ load_file("libpqwalreceiver", false);
+
+ /* Try to connect to the publisher. */
+ must_use_password = sub->passwordrequired && !sub->ownersuperuser;
+ wrconn = walrcv_connect(sub->conninfo, true, must_use_password,
+ sub->name, &err);
+ if (!wrconn)
+ ereport(ERROR,
+ (errcode(ERRCODE_CONNECTION_FAILURE),
+ errmsg("could not connect to the publisher: %s", err)));
+
+ PG_TRY();
+ {
+ walrcv_alter_slot(wrconn, sub->slotname, false);
+
+ ereport(NOTICE,
+ (errmsg("changed the failover state of replication slot \"%s\" on publisher to %s",
+ sub->slotname, "false")));
+ }
+ PG_FINALLY();
+ {
+ walrcv_disconnect(wrconn);
+ }
+ PG_END_TRY();
+ }
+
table_close(rel, RowExclusiveLock);
ObjectAddressSet(myself, SubscriptionRelationId, subid);
diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
index c9748539aa..45c94006ae 100644
--- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
+++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
@@ -74,8 +74,11 @@ static char *libpqrcv_create_slot(WalReceiverConn *conn,
const char *slotname,
bool temporary,
bool two_phase,
+ bool failover,
CRSSnapshotAction snapshot_action,
XLogRecPtr *lsn);
+static void libpqrcv_alter_slot(WalReceiverConn *conn, const char *slotname,
+ bool failover);
static pid_t libpqrcv_get_backend_pid(WalReceiverConn *conn);
static WalRcvExecResult *libpqrcv_exec(WalReceiverConn *conn,
const char *query,
@@ -96,6 +99,7 @@ static WalReceiverFunctionsType PQWalReceiverFunctions = {
.walrcv_receive = libpqrcv_receive,
.walrcv_send = libpqrcv_send,
.walrcv_create_slot = libpqrcv_create_slot,
+ .walrcv_alter_slot = libpqrcv_alter_slot,
.walrcv_get_backend_pid = libpqrcv_get_backend_pid,
.walrcv_exec = libpqrcv_exec,
.walrcv_disconnect = libpqrcv_disconnect
@@ -888,8 +892,8 @@ libpqrcv_send(WalReceiverConn *conn, const char *buffer, int nbytes)
*/
static char *
libpqrcv_create_slot(WalReceiverConn *conn, const char *slotname,
- bool temporary, bool two_phase, CRSSnapshotAction snapshot_action,
- XLogRecPtr *lsn)
+ bool temporary, bool two_phase, bool failover,
+ CRSSnapshotAction snapshot_action, XLogRecPtr *lsn)
{
PGresult *res;
StringInfoData cmd;
@@ -918,7 +922,8 @@ libpqrcv_create_slot(WalReceiverConn *conn, const char *slotname,
else
appendStringInfoChar(&cmd, ' ');
}
-
+ if (failover)
+ appendStringInfoString(&cmd, "FAILOVER, ");
if (use_new_options_syntax)
{
switch (snapshot_action)
@@ -987,6 +992,33 @@ libpqrcv_create_slot(WalReceiverConn *conn, const char *slotname,
return snapshot;
}
+/*
+ * Change the definition of the replication slot.
+ */
+static void
+libpqrcv_alter_slot(WalReceiverConn *conn, const char *slotname,
+ bool failover)
+{
+ StringInfoData cmd;
+ PGresult *res;
+
+ initStringInfo(&cmd);
+ appendStringInfo(&cmd, "ALTER_REPLICATION_SLOT %s ( FAILOVER %s )",
+ quote_identifier(slotname),
+ failover ? "true" : "false");
+
+ res = libpqrcv_PQexec(conn->streamConn, cmd.data);
+ pfree(cmd.data);
+
+ if (PQresultStatus(res) != PGRES_COMMAND_OK)
+ ereport(ERROR,
+ (errcode(ERRCODE_PROTOCOL_VIOLATION),
+ errmsg("could not alter replication slot \"%s\"",
+ slotname)));
+
+ PQclear(res);
+}
+
/*
* Return PID of remote backend process.
*/
diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c
index e8cc9ac552..74e9cfce1b 100644
--- a/src/backend/replication/logical/tablesync.c
+++ b/src/backend/replication/logical/tablesync.c
@@ -624,15 +624,28 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn)
* Note: If the subscription has no tables then leave the state as
* PENDING, which allows ALTER SUBSCRIPTION ... REFRESH PUBLICATION to
* work.
+ *
+ * Same goes for 'failover'. Enable it only if subscription has tables
+ * and all the tablesyncs have reached READY state.
*/
- if (MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING)
+ if (MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING ||
+ MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_PENDING)
{
CommandCounterIncrement(); /* make updates visible */
if (AllTablesyncsReady())
{
- ereport(LOG,
- (errmsg("logical replication apply worker for subscription \"%s\" will restart so that two_phase can be enabled",
- MySubscription->name)));
+ if (MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING)
+ ereport(LOG,
+ /* translator: %s is a subscription option */
+ (errmsg("logical replication apply worker for subscription \"%s\" will restart so that %s can be enabled",
+ MySubscription->name, "two_phase")));
+
+ if (MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_PENDING)
+ ereport(LOG,
+ /* translator: %s is a subscription option */
+ (errmsg("logical replication apply worker for subscription \"%s\" will restart so that %s can be enabled",
+ MySubscription->name, "failover")));
+
should_exit = true;
}
}
@@ -1430,7 +1443,8 @@ LogicalRepSyncTableStart(XLogRecPtr *origin_startpos)
*/
walrcv_create_slot(LogRepWorkerWalRcvConn,
slotname, false /* permanent */ , false /* two_phase */ ,
- CRS_USE_SNAPSHOT, origin_startpos);
+ false /* failover */ , CRS_USE_SNAPSHOT,
+ origin_startpos);
/*
* Setup replication origin tracking. The purpose of doing this before the
@@ -1732,10 +1746,12 @@ AllTablesyncsReady(void)
}
/*
- * Update the two_phase state of the specified subscription in pg_subscription.
+ * Update the twophase and/or failover state of the specified subscription
+ * in pg_subscription.
*/
void
-UpdateTwoPhaseState(Oid suboid, char new_state)
+EnableTwoPhaseFailoverTriState(Oid suboid, bool enable_twophase,
+ bool enable_failover)
{
Relation rel;
HeapTuple tup;
@@ -1743,9 +1759,8 @@ UpdateTwoPhaseState(Oid suboid, char new_state)
bool replaces[Natts_pg_subscription];
Datum values[Natts_pg_subscription];
- Assert(new_state == LOGICALREP_TWOPHASE_STATE_DISABLED ||
- new_state == LOGICALREP_TWOPHASE_STATE_PENDING ||
- new_state == LOGICALREP_TWOPHASE_STATE_ENABLED);
+ if (!enable_twophase && !enable_failover)
+ return;
rel = table_open(SubscriptionRelationId, RowExclusiveLock);
tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(suboid));
@@ -1759,9 +1774,21 @@ UpdateTwoPhaseState(Oid suboid, char new_state)
memset(nulls, false, sizeof(nulls));
memset(replaces, false, sizeof(replaces));
- /* And update/set two_phase state */
- values[Anum_pg_subscription_subtwophasestate - 1] = CharGetDatum(new_state);
- replaces[Anum_pg_subscription_subtwophasestate - 1] = true;
+ /* Update/set two_phase state if asked by the caller */
+ if (enable_twophase)
+ {
+ values[Anum_pg_subscription_subtwophasestate - 1] =
+ CharGetDatum(LOGICALREP_TWOPHASE_STATE_ENABLED);
+ replaces[Anum_pg_subscription_subtwophasestate - 1] = true;
+ }
+
+ /* Update/set failover state if asked by the caller */
+ if (enable_failover)
+ {
+ values[Anum_pg_subscription_subfailoverstate - 1] =
+ CharGetDatum(LOGICALREP_FAILOVER_STATE_ENABLED);
+ replaces[Anum_pg_subscription_subfailoverstate - 1] = true;
+ }
tup = heap_modify_tuple(tup, RelationGetDescr(rel),
values, nulls, replaces);
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 911835c5cb..3fe1f9953b 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -132,6 +132,33 @@
* avoid such deadlocks, we generate a unique GID (consisting of the
* subscription oid and the xid of the prepared transaction) for each prepare
* transaction on the subscriber.
+ *
+ * FAILOVER
+ * ----------------------
+ * The logical slot on the primary can be synced to the standby by specifying
+ * failover = true when creating the subscription. Enabling failover allows us
+ * to smoothly transition to the promoted standby, ensuring that we can
+ * subscribe to the new primary without losing any data.
+ *
+ * However, we do not enable failover for slots created by the table sync
+ * worker.
+ *
+ * Additionally, failover is not enabled for the main slot if the table sync is
+ * in progress. This is because if a failover occurs while the table sync
+ * worker has reached a certain state (SUBREL_STATE_FINISHEDCOPY or
+ * SUBREL_STATE_DATASYNC), replication will not be able to continue from the
+ * new primary node.
+ *
+ * As a result, we enable the failover option for the main slot only after the
+ * initial sync is complete. The failover option is implemented as a tri-state
+ * with values DISABLED, PENDING, and ENABLED. The state transition process
+ * between these values is the same as the two_phase option (see TWO_PHASE
+ * TRANSACTIONS for details).
+ *
+ * During the startup of the apply worker, it checks if all table syncs are in
+ * the READY state for a failover tri-state of PENDING. If so, it alters the
+ * main slot's failover property to true and updates the tri-state value from
+ * PENDING to ENABLED.
*-------------------------------------------------------------------------
*/
@@ -3947,6 +3974,7 @@ maybe_reread_subscription(void)
newsub->passwordrequired != MySubscription->passwordrequired ||
strcmp(newsub->origin, MySubscription->origin) != 0 ||
newsub->owner != MySubscription->owner ||
+ newsub->failoverstate != MySubscription->failoverstate ||
!equal(newsub->publications, MySubscription->publications))
{
if (am_parallel_apply_worker())
@@ -4482,6 +4510,8 @@ run_apply_worker()
TimeLineID startpointTLI;
char *err;
bool must_use_password;
+ bool twophase_pending;
+ bool failover_pending;
slotname = MySubscription->slotname;
@@ -4538,17 +4568,38 @@ run_apply_worker()
* Note: If the subscription has no tables then leave the state as
* PENDING, which allows ALTER SUBSCRIPTION ... REFRESH PUBLICATION to
* work.
+ *
+ * Same goes for 'failover'. It is enabled only if subscription has tables
+ * and all the tablesyncs have reached READY state, until then it remains
+ * as PENDING.
*/
- if (MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING &&
- AllTablesyncsReady())
+ twophase_pending =
+ (MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING);
+ failover_pending =
+ (MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_PENDING);
+
+ if ((twophase_pending || failover_pending) && AllTablesyncsReady())
{
/* Start streaming with two_phase enabled */
- options.proto.logical.twophase = true;
+ if (twophase_pending)
+ options.proto.logical.twophase = true;
+
+ if (failover_pending)
+ walrcv_alter_slot(LogRepWorkerWalRcvConn, slotname, true);
+
walrcv_startstreaming(LogRepWorkerWalRcvConn, &options);
StartTransactionCommand();
- UpdateTwoPhaseState(MySubscription->oid, LOGICALREP_TWOPHASE_STATE_ENABLED);
- MySubscription->twophasestate = LOGICALREP_TWOPHASE_STATE_ENABLED;
+
+ /* Update twophase and/or failover */
+ EnableTwoPhaseFailoverTriState(MySubscription->oid, twophase_pending,
+ failover_pending);
+ if (twophase_pending)
+ MySubscription->twophasestate = LOGICALREP_TWOPHASE_STATE_ENABLED;
+
+ if (failover_pending)
+ MySubscription->failoverstate = LOGICALREP_FAILOVER_STATE_ENABLED;
+
CommitTransactionCommand();
}
else
@@ -4557,11 +4608,15 @@ run_apply_worker()
}
ereport(DEBUG1,
- (errmsg_internal("logical replication apply worker for subscription \"%s\" two_phase is %s",
+ (errmsg_internal("logical replication apply worker for subscription \"%s\" two_phase is %s and failover is %s",
MySubscription->name,
MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_DISABLED ? "DISABLED" :
MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_PENDING ? "PENDING" :
MySubscription->twophasestate == LOGICALREP_TWOPHASE_STATE_ENABLED ? "ENABLED" :
+ "?",
+ MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_DISABLED ? "DISABLED" :
+ MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_PENDING ? "PENDING" :
+ MySubscription->failoverstate == LOGICALREP_FAILOVER_STATE_ENABLED ? "ENABLED" :
"?")));
/* Run the main loop. */
diff --git a/src/backend/replication/repl_gram.y b/src/backend/replication/repl_gram.y
index 95e126eb4d..ff3809e02f 100644
--- a/src/backend/replication/repl_gram.y
+++ b/src/backend/replication/repl_gram.y
@@ -64,6 +64,7 @@ Node *replication_parse_result;
%token K_START_REPLICATION
%token K_CREATE_REPLICATION_SLOT
%token K_DROP_REPLICATION_SLOT
+%token K_ALTER_REPLICATION_SLOT
%token K_TIMELINE_HISTORY
%token K_WAIT
%token K_TIMELINE
@@ -80,8 +81,9 @@ Node *replication_parse_result;
%type <node> command
%type <node> base_backup start_replication start_logical_replication
- create_replication_slot drop_replication_slot identify_system
- read_replication_slot timeline_history show upload_manifest
+ create_replication_slot drop_replication_slot
+ alter_replication_slot identify_system read_replication_slot
+ timeline_history show upload_manifest
%type <list> generic_option_list
%type <defelt> generic_option
%type <uintval> opt_timeline
@@ -112,6 +114,7 @@ command:
| start_logical_replication
| create_replication_slot
| drop_replication_slot
+ | alter_replication_slot
| read_replication_slot
| timeline_history
| show
@@ -259,6 +262,18 @@ drop_replication_slot:
}
;
+/* ALTER_REPLICATION_SLOT slot */
+alter_replication_slot:
+ K_ALTER_REPLICATION_SLOT IDENT '(' generic_option_list ')'
+ {
+ AlterReplicationSlotCmd *cmd;
+ cmd = makeNode(AlterReplicationSlotCmd);
+ cmd->slotname = $2;
+ cmd->options = $4;
+ $$ = (Node *) cmd;
+ }
+ ;
+
/*
* START_REPLICATION [SLOT slot] [PHYSICAL] %X/%X [TIMELINE %d]
*/
@@ -410,6 +425,7 @@ ident_or_keyword:
| K_START_REPLICATION { $$ = "start_replication"; }
| K_CREATE_REPLICATION_SLOT { $$ = "create_replication_slot"; }
| K_DROP_REPLICATION_SLOT { $$ = "drop_replication_slot"; }
+ | K_ALTER_REPLICATION_SLOT { $$ = "alter_replication_slot"; }
| K_TIMELINE_HISTORY { $$ = "timeline_history"; }
| K_WAIT { $$ = "wait"; }
| K_TIMELINE { $$ = "timeline"; }
diff --git a/src/backend/replication/repl_scanner.l b/src/backend/replication/repl_scanner.l
index 6fa625617b..e7def80065 100644
--- a/src/backend/replication/repl_scanner.l
+++ b/src/backend/replication/repl_scanner.l
@@ -125,6 +125,7 @@ TIMELINE { return K_TIMELINE; }
START_REPLICATION { return K_START_REPLICATION; }
CREATE_REPLICATION_SLOT { return K_CREATE_REPLICATION_SLOT; }
DROP_REPLICATION_SLOT { return K_DROP_REPLICATION_SLOT; }
+ALTER_REPLICATION_SLOT { return K_ALTER_REPLICATION_SLOT; }
TIMELINE_HISTORY { return K_TIMELINE_HISTORY; }
PHYSICAL { return K_PHYSICAL; }
RESERVE_WAL { return K_RESERVE_WAL; }
@@ -302,6 +303,7 @@ replication_scanner_is_replication_command(void)
case K_START_REPLICATION:
case K_CREATE_REPLICATION_SLOT:
case K_DROP_REPLICATION_SLOT:
+ case K_ALTER_REPLICATION_SLOT:
case K_READ_REPLICATION_SLOT:
case K_TIMELINE_HISTORY:
case K_UPLOAD_MANIFEST:
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 52da694c79..696376400e 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -90,7 +90,7 @@ typedef struct ReplicationSlotOnDisk
sizeof(ReplicationSlotOnDisk) - ReplicationSlotOnDiskConstantSize
#define SLOT_MAGIC 0x1051CA1 /* format identifier */
-#define SLOT_VERSION 3 /* version for new files */
+#define SLOT_VERSION 4 /* version for new files */
/* Control array for replication slot management */
ReplicationSlotCtlData *ReplicationSlotCtl = NULL;
@@ -248,10 +248,13 @@ ReplicationSlotValidateName(const char *name, int elevel)
* during getting changes, if the two_phase option is enabled it can skip
* prepare because by that time start decoding point has been moved. So the
* user will only get commit prepared.
+ * failover: If enabled, allows the slot to be synced to physical standbys so
+ * that logical replication can be resumed after failover.
*/
void
ReplicationSlotCreate(const char *name, bool db_specific,
- ReplicationSlotPersistency persistency, bool two_phase)
+ ReplicationSlotPersistency persistency,
+ bool two_phase, bool failover)
{
ReplicationSlot *slot = NULL;
int i;
@@ -311,6 +314,7 @@ ReplicationSlotCreate(const char *name, bool db_specific,
slot->data.persistency = persistency;
slot->data.two_phase = two_phase;
slot->data.two_phase_at = InvalidXLogRecPtr;
+ slot->data.failover = failover;
/* and then data only present in shared memory */
slot->just_dirtied = false;
@@ -679,6 +683,31 @@ ReplicationSlotDrop(const char *name, bool nowait)
ReplicationSlotDropAcquired();
}
+/*
+ * Change the definition of the slot identified by the specified name.
+ */
+void
+ReplicationSlotAlter(const char *name, bool failover)
+{
+ Assert(MyReplicationSlot == NULL);
+
+ ReplicationSlotAcquire(name, true);
+
+ if (SlotIsPhysical(MyReplicationSlot))
+ ereport(ERROR,
+ errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("cannot use %s with a physical replication slot",
+ "ALTER_REPLICATION_SLOT"));
+
+ SpinLockAcquire(&MyReplicationSlot->mutex);
+ MyReplicationSlot->data.failover = failover;
+ SpinLockRelease(&MyReplicationSlot->mutex);
+
+ ReplicationSlotMarkDirty();
+ ReplicationSlotSave();
+ ReplicationSlotRelease();
+}
+
/*
* Permanently drop the currently acquired replication slot.
*/
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index cad35dce7f..eb685089b3 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -42,7 +42,8 @@ create_physical_replication_slot(char *name, bool immediately_reserve,
/* acquire replication slot, this will check for conflicting names */
ReplicationSlotCreate(name, false,
- temporary ? RS_TEMPORARY : RS_PERSISTENT, false);
+ temporary ? RS_TEMPORARY : RS_PERSISTENT, false,
+ false);
if (immediately_reserve)
{
@@ -117,6 +118,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS)
static void
create_logical_replication_slot(char *name, char *plugin,
bool temporary, bool two_phase,
+ bool failover,
XLogRecPtr restart_lsn,
bool find_startpoint)
{
@@ -133,7 +135,8 @@ create_logical_replication_slot(char *name, char *plugin,
* error as well.
*/
ReplicationSlotCreate(name, true,
- temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase);
+ temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase,
+ failover);
/*
* Create logical decoding context to find start point or, if we don't
@@ -171,6 +174,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
Name plugin = PG_GETARG_NAME(1);
bool temporary = PG_GETARG_BOOL(2);
bool two_phase = PG_GETARG_BOOL(3);
+ bool failover = PG_GETARG_BOOL(4);
Datum result;
TupleDesc tupdesc;
HeapTuple tuple;
@@ -188,6 +192,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
NameStr(*plugin),
temporary,
two_phase,
+ failover,
InvalidXLogRecPtr,
true);
@@ -232,7 +237,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS)
Datum
pg_get_replication_slots(PG_FUNCTION_ARGS)
{
-#define PG_GET_REPLICATION_SLOTS_COLS 15
+#define PG_GET_REPLICATION_SLOTS_COLS 16
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
XLogRecPtr currlsn;
int slotno;
@@ -426,6 +431,8 @@ pg_get_replication_slots(PG_FUNCTION_ARGS)
}
}
+ values[i++] = BoolGetDatum(slot_contents.data.failover);
+
Assert(i == PG_GET_REPLICATION_SLOTS_COLS);
tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
@@ -693,6 +700,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
XLogRecPtr src_restart_lsn;
bool src_islogical;
bool temporary;
+ bool failover;
char *plugin;
Datum values[2];
bool nulls[2];
@@ -748,6 +756,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
src_islogical = SlotIsLogical(&first_slot_contents);
src_restart_lsn = first_slot_contents.data.restart_lsn;
temporary = (first_slot_contents.data.persistency == RS_TEMPORARY);
+ failover = first_slot_contents.data.failover;
plugin = logical_slot ? NameStr(first_slot_contents.data.plugin) : NULL;
/* Check type of replication slot */
@@ -787,6 +796,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
plugin,
temporary,
false,
+ failover,
src_restart_lsn,
false);
}
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index e00395ff2b..ffacd55e5c 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -387,7 +387,7 @@ WalReceiverMain(void)
"pg_walreceiver_%lld",
(long long int) walrcv_get_backend_pid(wrconn));
- walrcv_create_slot(wrconn, slotname, true, false, 0, NULL);
+ walrcv_create_slot(wrconn, slotname, true, false, false, 0, NULL);
SpinLockAcquire(&walrcv->mutex);
strlcpy(walrcv->slotname, slotname, NAMEDATALEN);
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 087031e9dc..58165ea614 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1126,12 +1126,13 @@ static void
parseCreateReplSlotOptions(CreateReplicationSlotCmd *cmd,
bool *reserve_wal,
CRSSnapshotAction *snapshot_action,
- bool *two_phase)
+ bool *two_phase, bool *failover)
{
ListCell *lc;
bool snapshot_action_given = false;
bool reserve_wal_given = false;
bool two_phase_given = false;
+ bool failover_given = false;
/* Parse options */
foreach(lc, cmd->options)
@@ -1181,6 +1182,15 @@ parseCreateReplSlotOptions(CreateReplicationSlotCmd *cmd,
two_phase_given = true;
*two_phase = defGetBoolean(defel);
}
+ else if (strcmp(defel->defname, "failover") == 0)
+ {
+ if (failover_given || cmd->kind != REPLICATION_KIND_LOGICAL)
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("conflicting or redundant options")));
+ failover_given = true;
+ *failover = defGetBoolean(defel);
+ }
else
elog(ERROR, "unrecognized option: %s", defel->defname);
}
@@ -1197,6 +1207,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
char *slot_name;
bool reserve_wal = false;
bool two_phase = false;
+ bool failover = false;
CRSSnapshotAction snapshot_action = CRS_EXPORT_SNAPSHOT;
DestReceiver *dest;
TupOutputState *tstate;
@@ -1206,13 +1217,14 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
Assert(!MyReplicationSlot);
- parseCreateReplSlotOptions(cmd, &reserve_wal, &snapshot_action, &two_phase);
+ parseCreateReplSlotOptions(cmd, &reserve_wal, &snapshot_action, &two_phase,
+ &failover);
if (cmd->kind == REPLICATION_KIND_PHYSICAL)
{
ReplicationSlotCreate(cmd->slotname, false,
cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT,
- false);
+ false, false);
if (reserve_wal)
{
@@ -1243,7 +1255,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
*/
ReplicationSlotCreate(cmd->slotname, true,
cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL,
- two_phase);
+ two_phase, failover);
/*
* Do options check early so that we can bail before calling the
@@ -1398,6 +1410,46 @@ DropReplicationSlot(DropReplicationSlotCmd *cmd)
ReplicationSlotDrop(cmd->slotname, !cmd->wait);
}
+/*
+ * Process extra options given to ALTER_REPLICATION_SLOT.
+ */
+static void
+ParseAlterReplSlotOptions(AlterReplicationSlotCmd *cmd, bool *failover)
+{
+ ListCell *lc;
+ bool failover_given = false;
+
+ /* Parse options */
+ foreach(lc, cmd->options)
+ {
+ DefElem *defel = (DefElem *) lfirst(lc);
+
+ if (strcmp(defel->defname, "failover") == 0)
+ {
+ if (failover_given)
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("conflicting or redundant options")));
+ failover_given = true;
+ *failover = defGetBoolean(defel);
+ }
+ else
+ elog(ERROR, "unrecognized option: %s", defel->defname);
+ }
+}
+
+/*
+ * Change the definition of a replication slot.
+ */
+static void
+AlterReplicationSlot(AlterReplicationSlotCmd *cmd)
+{
+ bool failover = false;
+
+ ParseAlterReplSlotOptions(cmd, &failover);
+ ReplicationSlotAlter(cmd->slotname, failover);
+}
+
/*
* Load previously initiated logical slot and prepare for sending data (via
* WalSndLoop).
@@ -1971,6 +2023,13 @@ exec_replication_command(const char *cmd_string)
EndReplicationCommand(cmdtag);
break;
+ case T_AlterReplicationSlotCmd:
+ cmdtag = "ALTER_REPLICATION_SLOT";
+ set_ps_display(cmdtag);
+ AlterReplicationSlot((AlterReplicationSlotCmd *) cmd_node);
+ EndReplicationCommand(cmdtag);
+ break;
+
case T_StartReplicationCmd:
{
StartReplicationCmd *cmd = (StartReplicationCmd *) cmd_node;
diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 22d1e6cf92..3f73adf2ee 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -4641,6 +4641,7 @@ getSubscriptions(Archive *fout)
int i_suborigin;
int i_suboriginremotelsn;
int i_subenabled;
+ int i_subfailoverstate;
int i,
ntups;
@@ -4706,10 +4707,18 @@ getSubscriptions(Archive *fout)
if (dopt->binary_upgrade && fout->remoteVersion >= 170000)
appendPQExpBufferStr(query, " o.remote_lsn AS suboriginremotelsn,\n"
- " s.subenabled\n");
+ " s.subenabled,\n");
else
appendPQExpBufferStr(query, " NULL AS suboriginremotelsn,\n"
- " false AS subenabled\n");
+ " false AS subenabled,\n");
+
+ if (fout->remoteVersion >= 170000)
+ appendPQExpBufferStr(query,
+ " s.subfailoverstate\n");
+ else
+ appendPQExpBuffer(query,
+ " '%c' AS subfailoverstate\n",
+ LOGICALREP_FAILOVER_STATE_DISABLED);
appendPQExpBufferStr(query,
"FROM pg_subscription s\n");
@@ -4748,6 +4757,7 @@ getSubscriptions(Archive *fout)
i_suborigin = PQfnumber(res, "suborigin");
i_suboriginremotelsn = PQfnumber(res, "suboriginremotelsn");
i_subenabled = PQfnumber(res, "subenabled");
+ i_subfailoverstate = PQfnumber(res, "subfailoverstate");
subinfo = pg_malloc(ntups * sizeof(SubscriptionInfo));
@@ -4792,6 +4802,8 @@ getSubscriptions(Archive *fout)
pg_strdup(PQgetvalue(res, i, i_suboriginremotelsn));
subinfo[i].subenabled =
pg_strdup(PQgetvalue(res, i, i_subenabled));
+ subinfo[i].subfailoverstate =
+ pg_strdup(PQgetvalue(res, i, i_subfailoverstate));
/* Decide whether we want to dump it */
selectDumpableObject(&(subinfo[i].dobj), fout);
@@ -4973,6 +4985,7 @@ dumpSubscription(Archive *fout, const SubscriptionInfo *subinfo)
int npubnames = 0;
int i;
char two_phase_disabled[] = {LOGICALREP_TWOPHASE_STATE_DISABLED, '\0'};
+ char failover_disabled[] = {LOGICALREP_FAILOVER_STATE_DISABLED, '\0'};
/* Do nothing in data-only dump */
if (dopt->dataOnly)
@@ -5020,6 +5033,9 @@ dumpSubscription(Archive *fout, const SubscriptionInfo *subinfo)
if (strcmp(subinfo->subtwophasestate, two_phase_disabled) != 0)
appendPQExpBufferStr(query, ", two_phase = on");
+ if (strcmp(subinfo->subfailoverstate, failover_disabled) != 0)
+ appendPQExpBufferStr(query, ", failover = true");
+
if (strcmp(subinfo->subdisableonerr, "t") == 0)
appendPQExpBufferStr(query, ", disable_on_error = true");
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9a34347cfc..946c9e22af 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -675,6 +675,7 @@ typedef struct _SubscriptionInfo
char *subpublications;
char *suborigin;
char *suboriginremotelsn;
+ char *subfailoverstate;
} SubscriptionInfo;
/*
diff --git a/src/bin/pg_upgrade/info.c b/src/bin/pg_upgrade/info.c
index 190dd53a42..b41a335b73 100644
--- a/src/bin/pg_upgrade/info.c
+++ b/src/bin/pg_upgrade/info.c
@@ -666,7 +666,7 @@ get_old_cluster_logical_slot_infos(DbInfo *dbinfo, bool live_check)
* started and stopped several times causing any temporary slots to be
* removed.
*/
- res = executeQueryOrDie(conn, "SELECT slot_name, plugin, two_phase, "
+ res = executeQueryOrDie(conn, "SELECT slot_name, plugin, two_phase, failover, "
"%s as caught_up, conflict_reason IS NOT NULL as invalid "
"FROM pg_catalog.pg_replication_slots "
"WHERE slot_type = 'logical' AND "
@@ -684,6 +684,7 @@ get_old_cluster_logical_slot_infos(DbInfo *dbinfo, bool live_check)
int i_slotname;
int i_plugin;
int i_twophase;
+ int i_failover;
int i_caught_up;
int i_invalid;
@@ -692,6 +693,7 @@ get_old_cluster_logical_slot_infos(DbInfo *dbinfo, bool live_check)
i_slotname = PQfnumber(res, "slot_name");
i_plugin = PQfnumber(res, "plugin");
i_twophase = PQfnumber(res, "two_phase");
+ i_failover = PQfnumber(res, "failover");
i_caught_up = PQfnumber(res, "caught_up");
i_invalid = PQfnumber(res, "invalid");
@@ -702,6 +704,7 @@ get_old_cluster_logical_slot_infos(DbInfo *dbinfo, bool live_check)
curr->slotname = pg_strdup(PQgetvalue(res, slotnum, i_slotname));
curr->plugin = pg_strdup(PQgetvalue(res, slotnum, i_plugin));
curr->two_phase = (strcmp(PQgetvalue(res, slotnum, i_twophase), "t") == 0);
+ curr->failover = (strcmp(PQgetvalue(res, slotnum, i_failover), "t") == 0);
curr->caught_up = (strcmp(PQgetvalue(res, slotnum, i_caught_up), "t") == 0);
curr->invalid = (strcmp(PQgetvalue(res, slotnum, i_invalid), "t") == 0);
}
diff --git a/src/bin/pg_upgrade/pg_upgrade.c b/src/bin/pg_upgrade/pg_upgrade.c
index 14a36f0503..10c94a6c1f 100644
--- a/src/bin/pg_upgrade/pg_upgrade.c
+++ b/src/bin/pg_upgrade/pg_upgrade.c
@@ -916,8 +916,10 @@ create_logical_replication_slots(void)
appendStringLiteralConn(query, slot_info->slotname, conn);
appendPQExpBuffer(query, ", ");
appendStringLiteralConn(query, slot_info->plugin, conn);
- appendPQExpBuffer(query, ", false, %s);",
- slot_info->two_phase ? "true" : "false");
+
+ appendPQExpBuffer(query, ", false, %s, %s);",
+ slot_info->two_phase ? "true" : "false",
+ slot_info->failover ? "true" : "false");
PQclear(executeQueryOrDie(conn, "%s", query->data));
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index a1d08c3dab..d9a848cbfd 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -160,6 +160,8 @@ typedef struct
bool two_phase; /* can the slot decode 2PC? */
bool caught_up; /* has the slot caught up to latest changes? */
bool invalid; /* if true, the slot is unusable */
+ bool failover; /* is the slot designated to be synced to the
+ * physical standby? */
} LogicalSlotInfo;
typedef struct
diff --git a/src/bin/pg_upgrade/t/003_logical_slots.pl b/src/bin/pg_upgrade/t/003_logical_slots.pl
index 0e7014ecce..a1f787019d 100644
--- a/src/bin/pg_upgrade/t/003_logical_slots.pl
+++ b/src/bin/pg_upgrade/t/003_logical_slots.pl
@@ -159,7 +159,7 @@ $sub->start;
$sub->safe_psql(
'postgres', qq[
CREATE TABLE tbl (a int);
- CREATE SUBSCRIPTION regress_sub CONNECTION '$old_connstr' PUBLICATION regress_pub WITH (two_phase = 'true')
+ CREATE SUBSCRIPTION regress_sub CONNECTION '$old_connstr' PUBLICATION regress_pub WITH (two_phase = 'true', failover = 'true')
]);
$sub->wait_for_subscription_sync($oldpub, 'regress_sub');
@@ -179,8 +179,8 @@ command_ok([@pg_upgrade_cmd], 'run of pg_upgrade of old cluster');
# Check that the slot 'regress_sub' has migrated to the new cluster
$newpub->start;
my $result = $newpub->safe_psql('postgres',
- "SELECT slot_name, two_phase FROM pg_replication_slots");
-is($result, qq(regress_sub|t), 'check the slot exists on new cluster');
+ "SELECT slot_name, two_phase, failover FROM pg_replication_slots");
+is($result, qq(regress_sub|t|t), 'check the slot exists on new cluster');
# Update the connection
my $new_connstr = $newpub->connstr . ' dbname=postgres';
diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 37f9516320..d37c70610c 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -6563,7 +6563,8 @@ describeSubscriptions(const char *pattern, bool verbose)
PGresult *res;
printQueryOpt myopt = pset.popt;
static const bool translate_columns[] = {false, false, false, false,
- false, false, false, false, false, false, false, false, false, false};
+ false, false, false, false, false, false, false, false, false, false,
+ false};
if (pset.sversion < 100000)
{
@@ -6627,6 +6628,11 @@ describeSubscriptions(const char *pattern, bool verbose)
gettext_noop("Password required"),
gettext_noop("Run as owner?"));
+ if (pset.sversion >= 170000)
+ appendPQExpBuffer(&buf,
+ ", subfailoverstate AS \"%s\"\n",
+ gettext_noop("Failover"));
+
appendPQExpBuffer(&buf,
", subsynccommit AS \"%s\"\n"
", subconninfo AS \"%s\"\n",
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 00770a0e6b..e468fe173b 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -3327,7 +3327,7 @@ psql_completion(const char *text, int start, int end)
/* Complete "CREATE SUBSCRIPTION <name> ... WITH ( <opt>" */
else if (HeadMatches("CREATE", "SUBSCRIPTION") && TailMatches("WITH", "("))
COMPLETE_WITH("binary", "connect", "copy_data", "create_slot",
- "disable_on_error", "enabled", "origin",
+ "disable_on_error", "enabled", "failover", "origin",
"password_required", "run_as_owner", "slot_name",
"streaming", "synchronous_commit", "two_phase");
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 7979392776..f40726c4f7 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11115,17 +11115,17 @@
proname => 'pg_get_replication_slots', prorows => '10', proisstrict => 'f',
proretset => 't', provolatile => 's', prorettype => 'record',
proargtypes => '',
- proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text}',
- proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
- proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflict_reason}',
+ proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text,bool}',
+ proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+ proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflict_reason,failover}',
prosrc => 'pg_get_replication_slots' },
{ oid => '3786', descr => 'set up a logical replication slot',
proname => 'pg_create_logical_replication_slot', provolatile => 'v',
proparallel => 'u', prorettype => 'record',
- proargtypes => 'name name bool bool',
- proallargtypes => '{name,name,bool,bool,name,pg_lsn}',
- proargmodes => '{i,i,i,i,o,o}',
- proargnames => '{slot_name,plugin,temporary,twophase,slot_name,lsn}',
+ proargtypes => 'name name bool bool bool',
+ proallargtypes => '{name,name,bool,bool,bool,name,pg_lsn}',
+ proargmodes => '{i,i,i,i,i,o,o}',
+ proargnames => '{slot_name,plugin,temporary,twophase,failover,slot_name,lsn}',
prosrc => 'pg_create_logical_replication_slot' },
{ oid => '4222',
descr => 'copy a logical replication slot, changing temporality and plugin',
diff --git a/src/include/catalog/pg_subscription.h b/src/include/catalog/pg_subscription.h
index ca32625585..e6e0f02fd3 100644
--- a/src/include/catalog/pg_subscription.h
+++ b/src/include/catalog/pg_subscription.h
@@ -31,6 +31,14 @@
#define LOGICALREP_TWOPHASE_STATE_PENDING 'p'
#define LOGICALREP_TWOPHASE_STATE_ENABLED 'e'
+/*
+ * failover tri-state values. See comments atop worker.c to know more about
+ * these states.
+ */
+#define LOGICALREP_FAILOVER_STATE_DISABLED 'd'
+#define LOGICALREP_FAILOVER_STATE_PENDING 'p'
+#define LOGICALREP_FAILOVER_STATE_ENABLED 'e'
+
/*
* The subscription will request the publisher to only send changes that do not
* have any origin.
@@ -93,6 +101,8 @@ CATALOG(pg_subscription,6100,SubscriptionRelationId) BKI_SHARED_RELATION BKI_ROW
bool subrunasowner; /* True if replication should execute as the
* subscription owner */
+ char subfailoverstate; /* Failover state */
+
#ifdef CATALOG_VARLEN /* variable-length fields start here */
/* Connection string to the publisher */
text subconninfo BKI_FORCE_NOT_NULL;
@@ -145,6 +155,7 @@ typedef struct Subscription
List *publications; /* List of publication names to subscribe to */
char *origin; /* Only publish data originating from the
* specified origin */
+ char failoverstate; /* Allow slot to be synchronized for failover */
} Subscription;
/* Disallow streaming in-progress transactions. */
diff --git a/src/include/nodes/replnodes.h b/src/include/nodes/replnodes.h
index af0a333f1a..ed23333e92 100644
--- a/src/include/nodes/replnodes.h
+++ b/src/include/nodes/replnodes.h
@@ -72,6 +72,18 @@ typedef struct DropReplicationSlotCmd
} DropReplicationSlotCmd;
+/* ----------------------
+ * ALTER_REPLICATION_SLOT command
+ * ----------------------
+ */
+typedef struct AlterReplicationSlotCmd
+{
+ NodeTag type;
+ char *slotname;
+ List *options;
+} AlterReplicationSlotCmd;
+
+
/* ----------------------
* START_REPLICATION command
* ----------------------
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index 9e39aaf303..585ccbb504 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -111,6 +111,12 @@ typedef struct ReplicationSlotPersistentData
/* plugin name */
NameData plugin;
+
+ /*
+ * Is this a failover slot (sync candidate for physical standbys)? Only
+ * relevant for logical slots on the primary server.
+ */
+ bool failover;
} ReplicationSlotPersistentData;
/*
@@ -218,9 +224,10 @@ extern void ReplicationSlotsShmemInit(void);
/* management of individual slots */
extern void ReplicationSlotCreate(const char *name, bool db_specific,
ReplicationSlotPersistency persistency,
- bool two_phase);
+ bool two_phase, bool failover);
extern void ReplicationSlotPersist(void);
extern void ReplicationSlotDrop(const char *name, bool nowait);
+extern void ReplicationSlotAlter(const char *name, bool failover);
extern void ReplicationSlotAcquire(const char *name, bool nowait);
extern void ReplicationSlotRelease(void);
diff --git a/src/include/replication/walreceiver.h b/src/include/replication/walreceiver.h
index 0899891cdb..f566a99ba1 100644
--- a/src/include/replication/walreceiver.h
+++ b/src/include/replication/walreceiver.h
@@ -355,9 +355,20 @@ typedef char *(*walrcv_create_slot_fn) (WalReceiverConn *conn,
const char *slotname,
bool temporary,
bool two_phase,
+ bool failover,
CRSSnapshotAction snapshot_action,
XLogRecPtr *lsn);
+/*
+ * walrcv_alter_slot_fn
+ *
+ * Change the definition of a replication slot. Currently, it only supports
+ * changing the failover property of the slot.
+ */
+typedef void (*walrcv_alter_slot_fn) (WalReceiverConn *conn,
+ const char *slotname,
+ bool failover);
+
/*
* walrcv_get_backend_pid_fn
*
@@ -399,6 +410,7 @@ typedef struct WalReceiverFunctionsType
walrcv_receive_fn walrcv_receive;
walrcv_send_fn walrcv_send;
walrcv_create_slot_fn walrcv_create_slot;
+ walrcv_alter_slot_fn walrcv_alter_slot;
walrcv_get_backend_pid_fn walrcv_get_backend_pid;
walrcv_exec_fn walrcv_exec;
walrcv_disconnect_fn walrcv_disconnect;
@@ -428,8 +440,10 @@ extern PGDLLIMPORT WalReceiverFunctionsType *WalReceiverFunctions;
WalReceiverFunctions->walrcv_receive(conn, buffer, wait_fd)
#define walrcv_send(conn, buffer, nbytes) \
WalReceiverFunctions->walrcv_send(conn, buffer, nbytes)
-#define walrcv_create_slot(conn, slotname, temporary, two_phase, snapshot_action, lsn) \
- WalReceiverFunctions->walrcv_create_slot(conn, slotname, temporary, two_phase, snapshot_action, lsn)
+#define walrcv_create_slot(conn, slotname, temporary, two_phase, failover, snapshot_action, lsn) \
+ WalReceiverFunctions->walrcv_create_slot(conn, slotname, temporary, two_phase, failover, snapshot_action, lsn)
+#define walrcv_alter_slot(conn, slotname, failover) \
+ WalReceiverFunctions->walrcv_alter_slot(conn, slotname, failover)
#define walrcv_get_backend_pid(conn) \
WalReceiverFunctions->walrcv_get_backend_pid(conn)
#define walrcv_exec(conn, exec, nRetTypes, retTypes) \
diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h
index 515aefd519..4e1f6e7df9 100644
--- a/src/include/replication/worker_internal.h
+++ b/src/include/replication/worker_internal.h
@@ -256,7 +256,8 @@ extern void ReplicationOriginNameForLogicalRep(Oid suboid, Oid relid,
char *originname, Size szoriginname);
extern bool AllTablesyncsReady(void);
-extern void UpdateTwoPhaseState(Oid suboid, char new_state);
+extern void EnableTwoPhaseFailoverTriState(Oid suboid, bool enable_twophase,
+ bool enable_failover);
extern void process_syncing_tables(XLogRecPtr current_lsn);
extern void invalidate_syncing_table_states(Datum arg, int cacheid,
diff --git a/src/test/recovery/t/050_standby_failover_slots_sync.pl b/src/test/recovery/t/050_standby_failover_slots_sync.pl
new file mode 100644
index 0000000000..796bf0a4af
--- /dev/null
+++ b/src/test/recovery/t/050_standby_failover_slots_sync.pl
@@ -0,0 +1,102 @@
+
+# Copyright (c) 2023, PostgreSQL Global Development Group
+
+use strict;
+use warnings;
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+##################################################
+# Test that when a subscription with failover enabled is created, it will alter
+# the failover property of the corresponding slot on the publisher.
+##################################################
+
+# Create publisher
+my $publisher = PostgreSQL::Test::Cluster->new('publisher');
+$publisher->init(allows_streaming => 'logical');
+$publisher->start;
+
+$publisher->safe_psql(
+ 'postgres', qq[
+ CREATE TABLE tab_int (a int PRIMARY KEY);
+ CREATE PUBLICATION regress_mypub FOR TABLE tab_int;
+]);
+
+my $publisher_connstr = $publisher->connstr . ' dbname=postgres';
+
+# Create a subscriber node, wait for sync to complete
+my $subscriber1 = PostgreSQL::Test::Cluster->new('subscriber1');
+$subscriber1->init;
+$subscriber1->start;
+
+# Create a slot on the publisher with failover disabled
+$publisher->safe_psql('postgres',
+ "SELECT 'init' FROM pg_create_logical_replication_slot('lsub1_slot', 'pgoutput', false, false, false);"
+);
+
+# Confirm that the failover flag on the slot is turned off
+is( $publisher->safe_psql(
+ 'postgres',
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ ),
+ "f",
+ 'logical slot has failover false on the publisher');
+
+# Create another subscription (using the same slot created above) that enables
+# failover.
+$subscriber1->safe_psql(
+ 'postgres', qq[
+ CREATE TABLE tab_int (a int PRIMARY KEY);
+ CREATE SUBSCRIPTION regress_mysub1 CONNECTION '$publisher_connstr' PUBLICATION regress_mypub WITH (slot_name = lsub1_slot, copy_data=false, failover = true, create_slot = false);
+]);
+
+# Confirm that the failover flag on the slot has now been turned on
+is( $publisher->safe_psql(
+ 'postgres',
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ ),
+ "t",
+ 'logical slot has failover true on the publisher');
+
+##################################################
+# Test if changing the failover property of a subscription updates the
+# corresponding failover property of the slot.
+##################################################
+
+$subscriber1->safe_psql('postgres', "ALTER SUBSCRIPTION regress_mysub1 DISABLE");
+
+# Wait for the replication slot to become inactive on the publisher
+$publisher->poll_query_until(
+ 'postgres',
+ "SELECT COUNT(*) FROM pg_catalog.pg_replication_slots WHERE slot_name = 'lsub1_slot' AND active='f'",
+ 1);
+
+# Disable failover
+$subscriber1->safe_psql('postgres',
+ "ALTER SUBSCRIPTION regress_mysub1 SET (failover = false)");
+
+# Confirm that the failover flag on the slot has now been turned off
+is( $publisher->safe_psql(
+ 'postgres',
+ q{SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';}
+ ),
+ "f",
+ 'logical slot has failover false on the publisher');
+
+# Enable failover and the subscription
+$subscriber1->safe_psql(
+ 'postgres', qq[
+ ALTER SUBSCRIPTION regress_mysub1 SET (failover = true);
+ ALTER SUBSCRIPTION regress_mysub1 ENABLE;
+]);
+
+# Confirm that the failover flag on the slot has now been turned on
+ok( $publisher->poll_query_until(
+ 'postgres',
+ "SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';"),
+ 'logical slot has failover true on the publisher');
+
+$subscriber1->safe_psql('postgres', "DROP SUBSCRIPTION regress_mysub1");
+
+done_testing();
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index d878a971df..acc2339b49 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1473,8 +1473,9 @@ pg_replication_slots| SELECT l.slot_name,
l.wal_status,
l.safe_wal_size,
l.two_phase,
- l.conflict_reason
- FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflict_reason)
+ l.conflict_reason,
+ l.failover
+ FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflict_reason, failover)
LEFT JOIN pg_database d ON ((l.datoid = d.oid)));
pg_roles| SELECT pg_authid.rolname,
pg_authid.rolsuper,
diff --git a/src/test/regress/expected/subscription.out b/src/test/regress/expected/subscription.out
index b15eddbff3..96c614332c 100644
--- a/src/test/regress/expected/subscription.out
+++ b/src/test/regress/expected/subscription.out
@@ -116,18 +116,18 @@ CREATE SUBSCRIPTION regress_testsub4 CONNECTION 'dbname=regress_doesnotexist' PU
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+ regress_testsub4
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f | {testpub} | f | off | d | f | none | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f | {testpub} | f | off | d | f | none | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub4 SET (origin = any);
\dRs+ regress_testsub4
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
DROP SUBSCRIPTION regress_testsub3;
@@ -145,10 +145,10 @@ ALTER SUBSCRIPTION regress_testsub CONNECTION 'foobar';
ERROR: invalid connection string syntax: missing "=" after "foobar" in connection info string
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET PUBLICATION testpub2, testpub3 WITH (refresh = false);
@@ -157,10 +157,10 @@ ALTER SUBSCRIPTION regress_testsub SET (slot_name = 'newname');
ALTER SUBSCRIPTION regress_testsub SET (password_required = false);
ALTER SUBSCRIPTION regress_testsub SET (run_as_owner = true);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | f | t | off | dbname=regress_doesnotexist2 | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | f | t | d | off | dbname=regress_doesnotexist2 | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (password_required = true);
@@ -176,10 +176,10 @@ ERROR: unrecognized subscription parameter: "create_slot"
-- ok
ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/12345');
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist2 | 0/12345
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist2 | 0/12345
(1 row)
-- ok - with lsn = NONE
@@ -188,10 +188,10 @@ ALTER SUBSCRIPTION regress_testsub SKIP (lsn = NONE);
ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/0');
ERROR: invalid WAL location (LSN): 0/0
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist2 | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist2 | 0/0
(1 row)
BEGIN;
@@ -223,10 +223,10 @@ ALTER SUBSCRIPTION regress_testsub_foo SET (synchronous_commit = foobar);
ERROR: invalid value for parameter "synchronous_commit": "foobar"
HINT: Available values: local, remote_write, remote_apply, on, off.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
----------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+------------------------------+----------
- regress_testsub_foo | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | local | dbname=regress_doesnotexist2 | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+---------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
+ regress_testsub_foo | regress_subscription_user | f | {testpub2,testpub3} | f | off | d | f | any | t | f | d | local | dbname=regress_doesnotexist2 | 0/0
(1 row)
-- rename back to keep the rest simple
@@ -255,19 +255,19 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | t | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | t | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (binary = false);
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
DROP SUBSCRIPTION regress_testsub;
@@ -279,27 +279,27 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | on | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | on | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (streaming = parallel);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | parallel | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | parallel | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (streaming = false);
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
-- fail - publication already exists
@@ -314,10 +314,10 @@ ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refr
ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refresh = false);
ERROR: publication "testpub1" is already in subscription "regress_testsub"
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub,testpub1,testpub2} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub,testpub1,testpub2} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
-- fail - publication used more than once
@@ -332,10 +332,10 @@ ERROR: publication "testpub3" is not in subscription "regress_testsub"
-- ok - delete publications
ALTER SUBSCRIPTION regress_testsub DROP PUBLICATION testpub1, testpub2 WITH (refresh = false);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
DROP SUBSCRIPTION regress_testsub;
@@ -371,10 +371,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | p | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | p | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
--fail - alter of two_phase option not supported.
@@ -383,10 +383,10 @@ ERROR: unrecognized subscription parameter: "two_phase"
-- but can alter streaming when two_phase enabled
ALTER SUBSCRIPTION regress_testsub SET (streaming = true);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | on | p | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | on | p | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -396,10 +396,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | on | p | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | on | p | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -412,18 +412,31 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
WARNING: subscription was created, but is not connected
HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
\dRs+
- List of subscriptions
- Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Synchronous commit | Conninfo | Skip LSN
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | t | any | t | f | off | dbname=regress_doesnotexist | 0/0
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | t | any | t | f | d | off | dbname=regress_doesnotexist | 0/0
+(1 row)
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+-- test failover option
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, failover = true);
+WARNING: subscription was created, but is not connected
+HINT: To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
+\dRs+
+ List of subscriptions
+ Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit | Conninfo | Skip LSN
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f | {testpub} | f | off | d | f | any | t | f | p | off | dbname=regress_doesnotexist | 0/0
(1 row)
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
diff --git a/src/test/regress/sql/subscription.sql b/src/test/regress/sql/subscription.sql
index 444e563ff3..e4601158b3 100644
--- a/src/test/regress/sql/subscription.sql
+++ b/src/test/regress/sql/subscription.sql
@@ -290,6 +290,14 @@ ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
DROP SUBSCRIPTION regress_testsub;
+-- test failover option
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, failover = true);
+
+\dRs+
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+
-- let's do some tests with pg_create_subscription rather than superuser
SET SESSION AUTHORIZATION regress_subscription_user3;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 5fd46b7bd1..9b67986914 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -85,6 +85,7 @@ AlterOwnerStmt
AlterPolicyStmt
AlterPublicationAction
AlterPublicationStmt
+AlterReplicationSlotCmd
AlterRoleSetStmt
AlterRoleStmt
AlterSeqStmt
@@ -3874,6 +3875,7 @@ varattrib_1b_e
varattrib_4b
vbits
verifier_context
+walrcv_alter_slot_fn
walrcv_check_conninfo_fn
walrcv_connect_fn
walrcv_create_slot_fn
--
2.34.1
[application/octet-stream] v57-0002-Add-logical-slot-sync-capability-to-the-physical.patch (91.5K, ../CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com/5-v57-0002-Add-logical-slot-sync-capability-to-the-physical.patch)
download | inline diff:
From 07a27c150897971049ed1edacdc62504c66708e4 Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Thu, 4 Jan 2024 09:37:50 +0530
Subject: [PATCH v57 2/4] Add logical slot sync capability to the physical
standby
This patch implements synchronization of logical replication slots
from the primary server to the physical standby so that logical
replication can be resumed after failover.
GUC 'enable_syncslot' enables a physical standby to synchronize failover
logical replication slots from the primary server.
The logical replication slots on the primary can be synchronized to the hot
standby by enabling the failover option during slot creation and setting
'enable_syncslot' on the standby. For the synchronization to work, it is
mandatory to have a physical replication slot between the primary and the
standby, and hot_standby_feedback must be enabled on the standby.
All the failover logical replication slots on the primary (assuming
configurations are appropriate) are automatically created on the physical
standbys and are synced periodically. Slot-sync worker on the standby server
ping the primary server at regular intervals to get the necessary
failover logical slots information and create/update the slots locally.
The nap time of the worker is tuned according to the activity on the primary.
The worker starts with nap time of 10ms and if no activity is observed on
the primary for some time, then nap time is increased to 10sec. If
activity is observed again, nap time is reduced back to 10ms.
The logical slots created by slot-sync worker on physical standbys are not
allowed to be dropped or consumed. Any attempt to perform logical decoding on
such slots will result in an error.
If a logical slot is invalidated on the primary, slot on the standby is also
invalidated.
If a logical slot on the primary is valid but is invalidated on the standby,
then that slot is dropped and recreated on the standby in next sync-cycle
provided the slot still exists on the primary server. It is okay to recreate
such slots as long as these are not consumable on the standby (which is the
case currently). This situation may occur due to the following reasons:
- The max_slot_wal_keep_size on the standby is insufficient to retain WAL
records from the restart_lsn of the slot.
- primary_slot_name is temporarily reset to null and the physical slot is
removed.
- The primary changes wal_level to a level lower than logical.
The slots synchronization status on the standby can be monitored using
'sync_state' column of pg_replication_slots view. The values are:
'none': for user slots,
'initiated': sync initiated for the slot but slot is not ready yet for periodic syncs,
'ready': ready for periodic syncs.
---
doc/src/sgml/bgworker.sgml | 65 +-
doc/src/sgml/config.sgml | 27 +-
doc/src/sgml/logicaldecoding.sgml | 31 +
doc/src/sgml/system-views.sgml | 35 +
src/backend/access/transam/xlogrecovery.c | 18 +
src/backend/catalog/system_views.sql | 3 +-
src/backend/postmaster/bgworker.c | 4 +
src/backend/postmaster/postmaster.c | 10 +
.../libpqwalreceiver/libpqwalreceiver.c | 41 +
src/backend/replication/logical/Makefile | 1 +
src/backend/replication/logical/logical.c | 25 +
src/backend/replication/logical/meson.build | 1 +
src/backend/replication/logical/slotsync.c | 1357 +++++++++++++++++
src/backend/replication/logical/worker.c | 15 +-
src/backend/replication/slot.c | 35 +-
src/backend/replication/slotfuncs.c | 27 +-
src/backend/replication/walsender.c | 4 +-
src/backend/storage/ipc/ipci.c | 2 +
src/backend/tcop/postgres.c | 11 +
.../utils/activity/wait_event_names.txt | 2 +
src/backend/utils/misc/guc_tables.c | 10 +
src/backend/utils/misc/postgresql.conf.sample | 1 +
src/include/catalog/pg_proc.dat | 6 +-
src/include/postmaster/bgworker.h | 1 +
src/include/replication/logicalworker.h | 1 +
src/include/replication/slot.h | 29 +-
src/include/replication/walreceiver.h | 18 +
src/include/replication/worker_internal.h | 11 +
.../t/050_standby_failover_slots_sync.pl | 185 ++-
src/test/regress/expected/rules.out | 5 +-
src/test/regress/expected/sysviews.out | 3 +-
src/tools/pgindent/typedefs.list | 2 +
32 files changed, 1951 insertions(+), 35 deletions(-)
create mode 100644 src/backend/replication/logical/slotsync.c
diff --git a/doc/src/sgml/bgworker.sgml b/doc/src/sgml/bgworker.sgml
index 2c393385a9..a7cfe6c58c 100644
--- a/doc/src/sgml/bgworker.sgml
+++ b/doc/src/sgml/bgworker.sgml
@@ -114,18 +114,59 @@ typedef struct BackgroundWorker
<para>
<structfield>bgw_start_time</structfield> is the server state during which
- <command>postgres</command> should start the process; it can be one of
- <literal>BgWorkerStart_PostmasterStart</literal> (start as soon as
- <command>postgres</command> itself has finished its own initialization; processes
- requesting this are not eligible for database connections),
- <literal>BgWorkerStart_ConsistentState</literal> (start as soon as a consistent state
- has been reached in a hot standby, allowing processes to connect to
- databases and run read-only queries), and
- <literal>BgWorkerStart_RecoveryFinished</literal> (start as soon as the system has
- entered normal read-write state). Note the last two values are equivalent
- in a server that's not a hot standby. Note that this setting only indicates
- when the processes are to be started; they do not stop when a different state
- is reached.
+ <command>postgres</command> should start the process. Note that this setting
+ only indicates when the processes are to be started; they do not stop when
+ a different state is reached. Possible values are:
+
+ <variablelist>
+ <varlistentry>
+ <term><literal>BgWorkerStart_PostmasterStart</literal></term>
+ <listitem>
+ <para>
+ <indexterm><primary>BgWorkerStart_PostmasterStart</primary></indexterm>
+ Start as soon as postgres itself has finished its own initialization;
+ processes requesting this are not eligible for database connections.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><literal>BgWorkerStart_ConsistentState</literal></term>
+ <listitem>
+ <para>
+ <indexterm><primary>BgWorkerStart_ConsistentState</primary></indexterm>
+ Start as soon as a consistent state has been reached in a hot-standby,
+ allowing processes to connect to databases and run read-only queries.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><literal>BgWorkerStart_ConsistentState_HotStandby</literal></term>
+ <listitem>
+ <para>
+ <indexterm><primary>BgWorkerStart_ConsistentState_HotStandby</primary></indexterm>
+ Same meaning as <literal>BgWorkerStart_ConsistentState</literal> but
+ it is more strict in terms of the server i.e. start the worker only
+ if it is hot-standby.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><literal>BgWorkerStart_RecoveryFinished</literal></term>
+ <listitem>
+ <para>
+ <indexterm><primary>BgWorkerStart_RecoveryFinished</primary></indexterm>
+ Start as soon as the system has entered normal read-write state. Note
+ that the <literal>BgWorkerStart_ConsistentState</literal> and
+ <literal>BgWorkerStart_RecoveryFinished</literal> are equivalent
+ in a server that's not a hot standby.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
</para>
<para>
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index f323bba018..cd9ae70c41 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4611,8 +4611,13 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
<varname>primary_conninfo</varname> string, or in a separate
<filename>~/.pgpass</filename> file on the standby server (use
<literal>replication</literal> as the database name).
- Do not specify a database name in the
- <varname>primary_conninfo</varname> string.
+ </para>
+ <para>
+ If slot synchronization is enabled (see
+ <xref linkend="guc-enable-syncslot"/>) then it is also
+ necessary to specify <literal>dbname</literal> in the
+ <varname>primary_conninfo</varname> string. This will only be used for
+ slot synchronization. It is ignored for streaming.
</para>
<para>
This parameter can only be set in the <filename>postgresql.conf</filename>
@@ -4937,6 +4942,24 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
</listitem>
</varlistentry>
+ <varlistentry id="guc-enable-syncslot" xreflabel="enable_syncslot">
+ <term><varname>enable_syncslot</varname> (<type>boolean</type>)
+ <indexterm>
+ <primary><varname>enable_syncslot</varname> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ It enables a physical standby to synchronize logical failover slots
+ from the primary server so that logical subscribers are not blocked
+ after failover.
+ </para>
+ <para>
+ It is disabled by default. This parameter can only be set in the
+ <filename>postgresql.conf</filename> file or on the server command line.
+ </para>
+ </listitem>
+ </varlistentry>
</variablelist>
</sect2>
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index cd152d4ced..de6cdbe2bc 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -346,6 +346,37 @@ postgres=# select * from pg_logical_slot_get_changes('regression_slot', NULL, NU
<function>pg_log_standby_snapshot</function> function on the primary.
</para>
+ <para>
+ A logical replication slot on the primary can be synchronized to the hot
+ standby by enabling the failover option during slot creation and setting
+ <xref linkend="guc-enable-syncslot"/> on the standby. For the synchronization
+ to work, it is mandatory to have a physical replication slot between the
+ primary and the standby, and <varname>hot_standby_feedback</varname> must
+ be enabled on the standby. It's also highly recommended that the said
+ physical replication slot is named in <varname>standby_slot_names</varname>
+ list on the primary, to prevent the subscriber from consuming changes
+ faster than the hot standby.
+ </para>
+
+ <para>
+ The ability to resume logical replication after failover depends upon the
+ <link linkend="view-pg-replication-slots">pg_replication_slots</link>.<structfield>sync_state</structfield>
+ value for the synchronized slots on the standby at the time of failover.
+ Only slots that have attained "ready" sync_state ('r') on the standby
+ before failover can be used for logical replication after failover. Slots
+ that have not yet reached 'r' state (they are still 'i') will be dropped,
+ therefore logical replication for those slots cannot be resumed. For
+ example, if the synchronized slot could not become sync-ready on the
+ standby due to a disabled subscription, then the subscription cannot be
+ resumed after failover even when it is enabled.
+ </para>
+ <para>
+ If the primary is idle, then the synchronized slots on the standby may
+ take a noticeable time to reach the ready ('r') sync_state. This can
+ be sped up by calling the
+ <function>pg_log_standby_snapshot</function> function on the primary.
+ </para>
+
<caution>
<para>
Replication slots persist across crashes and know nothing about the state
diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml
index c10880b200..5eb7d1bc8a 100644
--- a/doc/src/sgml/system-views.sgml
+++ b/doc/src/sgml/system-views.sgml
@@ -2566,6 +2566,41 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx
after failover. Always false for physical slots.
</para></entry>
</row>
+
+ <row>
+ <entry role="catalog_table_entry"><para role="column_definition">
+ <structfield>sync_state</structfield> <type>text</type>
+ </para>
+ <para>
+ Defines slot synchronization state. This is meaningful on the physical
+ standby which has configured <xref linkend="guc-enable-syncslot"/> = true.
+ Possible values are:
+ <itemizedlist>
+ <listitem>
+ <para><literal>none</literal> = for user created slots,
+ </para>
+ </listitem>
+ <listitem>
+ <para><literal>initiated</literal> = sync initiated for the slot but slot
+ is not ready yet for periodic syncs,
+ </para>
+ </listitem>
+ <listitem>
+ <para>
+ <literal>ready</literal> = ready for periodic syncs.
+ </para>
+ </listitem>
+ </itemizedlist>
+ </para>
+ <para>
+ The hot standby can have any of these sync_state values for the slots but
+ on a hot standby, the slots with state 'ready' and 'initiated' can neither
+ be used for logical decoding nor dropped by the user.
+ The sync_state has no meaning on the primary server; the primary
+ sync_state value is default 'none' for all slots but may (if leftover
+ from a promoted standby) also be 'ready'.
+ </para></entry>
+ </row>
</tbody>
</tgroup>
</table>
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index 1b48d7171a..d67c5c1793 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -50,6 +50,7 @@
#include "postmaster/startup.h"
#include "replication/slot.h"
#include "replication/walreceiver.h"
+#include "replication/worker_internal.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/latch.h"
@@ -1441,6 +1442,23 @@ FinishWalRecovery(void)
*/
XLogShutdownWalRcv();
+ /*
+ * Shutdown the slot sync workers to prevent potential conflicts between
+ * user processes and slotsync workers after a promotion. Additionally,
+ * drop any slots that have initiated but not yet completed the sync
+ * process.
+ *
+ * We do not update the sync_state from READY to NONE here, as any failed
+ * update could leave some slots in the 'NONE' state, causing issues during
+ * slot sync after restarting the server as a standby. While updating after
+ * switching to the new timeline is an option, it does not simplify the
+ * handling for both READY and NONE state slots. Therefore, we retain the
+ * READY state slots after promotion as they can provide useful information
+ * about their origin.
+ */
+ ShutDownSlotSync();
+ slotsync_drop_initiated_slots();
+
/*
* We are now done reading the xlog from stream. Turn off streaming
* recovery to force fetching the files (which would be required at end of
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 1e954147e5..df2d4bd01a 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1024,7 +1024,8 @@ CREATE VIEW pg_replication_slots AS
L.safe_wal_size,
L.two_phase,
L.conflict_reason,
- L.failover
+ L.failover,
+ L.sync_state
FROM pg_get_replication_slots() AS L
LEFT JOIN pg_database D ON (L.datoid = D.oid);
diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c
index 67f92c24db..46828b8a89 100644
--- a/src/backend/postmaster/bgworker.c
+++ b/src/backend/postmaster/bgworker.c
@@ -21,6 +21,7 @@
#include "postmaster/postmaster.h"
#include "replication/logicallauncher.h"
#include "replication/logicalworker.h"
+#include "replication/worker_internal.h"
#include "storage/dsm.h"
#include "storage/ipc.h"
#include "storage/latch.h"
@@ -129,6 +130,9 @@ static const struct
{
"ApplyWorkerMain", ApplyWorkerMain
},
+ {
+ "ReplSlotSyncWorkerMain", ReplSlotSyncWorkerMain
+ },
{
"ParallelApplyWorkerMain", ParallelApplyWorkerMain
},
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index feb471dd1d..d90d5d1576 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -116,6 +116,7 @@
#include "postmaster/walsummarizer.h"
#include "replication/logicallauncher.h"
#include "replication/walsender.h"
+#include "replication/worker_internal.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/pg_shmem.h"
@@ -1010,6 +1011,12 @@ PostmasterMain(int argc, char *argv[])
*/
ApplyLauncherRegister();
+ /*
+ * Register the slot sync worker here to kick start slot-sync operation
+ * sooner on the physical standby.
+ */
+ SlotSyncWorkerRegister();
+
/*
* process any libraries that should be preloaded at postmaster start
*/
@@ -5799,6 +5806,9 @@ bgworker_should_start_now(BgWorkerStartTime start_time)
case PM_HOT_STANDBY:
if (start_time == BgWorkerStart_ConsistentState)
return true;
+ if (start_time == BgWorkerStart_ConsistentState_HotStandby &&
+ pmState != PM_RUN)
+ return true;
/* fall through */
case PM_RECOVERY:
diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
index 45c94006ae..7a6ff557bc 100644
--- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
+++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
@@ -34,6 +34,7 @@
#include "utils/memutils.h"
#include "utils/pg_lsn.h"
#include "utils/tuplestore.h"
+#include "utils/varlena.h"
PG_MODULE_MAGIC;
@@ -58,6 +59,7 @@ static void libpqrcv_get_senderinfo(WalReceiverConn *conn,
char **sender_host, int *sender_port);
static char *libpqrcv_identify_system(WalReceiverConn *conn,
TimeLineID *primary_tli);
+static char *libpqrcv_get_dbname_from_conninfo(const char *conninfo);
static int libpqrcv_server_version(WalReceiverConn *conn);
static void libpqrcv_readtimelinehistoryfile(WalReceiverConn *conn,
TimeLineID tli, char **filename,
@@ -100,6 +102,7 @@ static WalReceiverFunctionsType PQWalReceiverFunctions = {
.walrcv_send = libpqrcv_send,
.walrcv_create_slot = libpqrcv_create_slot,
.walrcv_alter_slot = libpqrcv_alter_slot,
+ .walrcv_get_dbname_from_conninfo = libpqrcv_get_dbname_from_conninfo,
.walrcv_get_backend_pid = libpqrcv_get_backend_pid,
.walrcv_exec = libpqrcv_exec,
.walrcv_disconnect = libpqrcv_disconnect
@@ -418,6 +421,44 @@ libpqrcv_server_version(WalReceiverConn *conn)
return PQserverVersion(conn->streamConn);
}
+/*
+ * Get database name from the primary server's conninfo.
+ *
+ * If dbname is not found in connInfo, return NULL value.
+ */
+static char *
+libpqrcv_get_dbname_from_conninfo(const char *connInfo)
+{
+ PQconninfoOption *opts;
+ char *dbname = NULL;
+ char *err = NULL;
+
+ opts = PQconninfoParse(connInfo, &err);
+ if (opts == NULL)
+ {
+ /* The error string is malloc'd, so we must free it explicitly */
+ char *errcopy = err ? pstrdup(err) : "out of memory";
+
+ PQfreemem(err);
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("invalid connection string syntax: %s", errcopy)));
+ }
+
+ for (PQconninfoOption *opt = opts; opt->keyword != NULL; ++opt)
+ {
+ /*
+ * If multiple dbnames are specified, then the last one will be
+ * returned
+ */
+ if (strcmp(opt->keyword, "dbname") == 0 && opt->val &&
+ opt->val[0] != '\0')
+ dbname = pstrdup(opt->val);
+ }
+
+ return dbname;
+}
+
/*
* Start streaming WAL data from given streaming options.
*
diff --git a/src/backend/replication/logical/Makefile b/src/backend/replication/logical/Makefile
index 2dc25e37bb..ba03eeff1c 100644
--- a/src/backend/replication/logical/Makefile
+++ b/src/backend/replication/logical/Makefile
@@ -25,6 +25,7 @@ OBJS = \
proto.o \
relation.o \
reorderbuffer.o \
+ slotsync.o \
snapbuild.o \
tablesync.o \
worker.o
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index ca09c683f1..ee9f2445a8 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -524,6 +524,31 @@ CreateDecodingContext(XLogRecPtr start_lsn,
errmsg("replication slot \"%s\" was not created in this database",
NameStr(slot->data.name))));
+ if (RecoveryInProgress())
+ {
+ /*
+ * Do not allow consumption of a "synchronized" slot until the standby
+ * gets promoted.
+ */
+ if (slot->data.sync_state != SYNCSLOT_STATE_NONE)
+ ereport(ERROR,
+ errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot use replication slot \"%s\" for logical"
+ " decoding", NameStr(slot->data.name)),
+ errdetail("This slot is being synced from the primary server."),
+ errhint("Specify another replication slot."));
+ }
+ else
+ {
+ /*
+ * Slots in state SYNCSLOT_STATE_INITIATED should have been dropped on
+ * promotion.
+ */
+ if (slot->data.sync_state == SYNCSLOT_STATE_INITIATED)
+ elog(ERROR, "replication slot \"%s\" was not synced completely"
+ " from the primary server", NameStr(slot->data.name));
+ }
+
/*
* Check if slot has been invalidated due to max_slot_wal_keep_size. Avoid
* "cannot get changes" wording in this errmsg because that'd be
diff --git a/src/backend/replication/logical/meson.build b/src/backend/replication/logical/meson.build
index 1050eb2c09..3dec36a6de 100644
--- a/src/backend/replication/logical/meson.build
+++ b/src/backend/replication/logical/meson.build
@@ -11,6 +11,7 @@ backend_sources += files(
'proto.c',
'relation.c',
'reorderbuffer.c',
+ 'slotsync.c',
'snapbuild.c',
'tablesync.c',
'worker.c',
diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c
new file mode 100644
index 0000000000..a84ab020ee
--- /dev/null
+++ b/src/backend/replication/logical/slotsync.c
@@ -0,0 +1,1357 @@
+/*-------------------------------------------------------------------------
+ * slotsync.c
+ * PostgreSQL worker for synchronizing slots to a standby server from the
+ * primary server.
+ *
+ * Copyright (c) 2023, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * src/backend/replication/logical/slotsync.c
+ *
+ * This file contains the code for slot sync worker on a physical standby
+ * to fetch logical failover slots information from the primary server,
+ * create the slots on the standby and synchronize them periodically.
+ *
+ * While creating the slot on physical standby, if the local restart_lsn and/or
+ * local catalog_xmin is ahead of those on the remote then the worker cannot
+ * create the local slot in sync with the primary server because that would
+ * mean moving the local slot backwards and the standby might not have WALs
+ * retained for old LSN. In this case, the worker will wait for the primary
+ * server slot's restart_lsn and catalog_xmin to catch up with the local one
+ * before attempting the actual sync. Meanwhile, it will persist the slot with
+ * sync_state as SYNCSLOT_STATE_INITIATED('i'). Once the primary server catches
+ * up, it will move the slot to SYNCSLOT_STATE_READY('r') state and will perform
+ * the sync periodically.
+ *
+ * The worker also takes care of dropping the slots which were created by it
+ * and are currently not needed to be synchronized.
+ *
+ * It takes a nap of WORKER_DEFAULT_NAPTIME_MS before every next
+ * synchronization. If there is no activity observed on the primary server for
+ * some time, the nap time is increased to WORKER_INACTIVITY_NAPTIME_MS, but if
+ * any activity is observed, the nap time reverts to the default value.
+ *---------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "access/genam.h"
+#include "access/table.h"
+#include "access/xlogrecovery.h"
+#include "catalog/pg_database.h"
+#include "commands/dbcommands.h"
+#include "pgstat.h"
+#include "postmaster/bgworker.h"
+#include "postmaster/interrupt.h"
+#include "replication/logical.h"
+#include "replication/logicallauncher.h"
+#include "replication/logicalworker.h"
+#include "replication/walreceiver.h"
+#include "replication/worker_internal.h"
+#include "storage/ipc.h"
+#include "storage/procarray.h"
+#include "tcop/tcopprot.h"
+#include "utils/builtins.h"
+#include "utils/fmgroids.h"
+#include "utils/guc_hooks.h"
+#include "utils/pg_lsn.h"
+#include "utils/varlena.h"
+
+/*
+ * Structure to hold information fetched from the primary server about a logical
+ * replication slot.
+ */
+typedef struct RemoteSlot
+{
+ char *name;
+ char *plugin;
+ char *database;
+ bool two_phase;
+ bool failover;
+ XLogRecPtr restart_lsn;
+ XLogRecPtr confirmed_lsn;
+ TransactionId catalog_xmin;
+
+ /* RS_INVAL_NONE if valid, or the reason of invalidation */
+ ReplicationSlotInvalidationCause invalidated;
+} RemoteSlot;
+
+/*
+ * Struct for sharing information between startup process and slot
+ * sync worker.
+ *
+ * Slot sync worker's pid is needed by startup process in order to
+ * shut it down during promotion.
+ */
+typedef struct SlotSyncWorkerCtxStruct
+{
+ pid_t pid;
+ slock_t mutex;
+} SlotSyncWorkerCtxStruct;
+
+SlotSyncWorkerCtxStruct *SlotSyncWorker = NULL;
+
+/* GUC variable */
+bool enable_syncslot = false;
+
+/* The last sync-cycle time when the worker updated any of the slots. */
+static TimestampTz last_update_time;
+
+/* Worker's nap time in case of regular activity on the primary server */
+#define WORKER_DEFAULT_NAPTIME_MS 10L /* 10 ms */
+
+/* Worker's nap time in case of no-activity on the primary server */
+#define WORKER_INACTIVITY_NAPTIME_MS 10000L /* 10 sec */
+
+/*
+ * Inactivity Threshold in ms before increasing nap time of worker.
+ *
+ * If the lsn of slot being monitored did not change for this threshold time,
+ * then increase nap time of current worker from WORKER_DEFAULT_NAPTIME_MS to
+ * WORKER_INACTIVITY_NAPTIME_MS.
+ */
+#define WORKER_INACTIVITY_THRESHOLD_MS 10000L /* 10 sec */
+
+static void ProcessSlotSyncInterrupts(WalReceiverConn *wrconn);
+
+/*
+ * Wait for remote slot to pass locally reserved position.
+ *
+ * Ping and wait for the primary server for
+ * WAIT_PRIMARY_CATCHUP_ATTEMPTS during a slot creation, if it still
+ * does not catch up, abort the wait. The ones for which wait is aborted will
+ * attempt the wait and sync in the next sync-cycle.
+ *
+ * If passed, *wait_attempts_exceeded will be set to true only if this
+ * function exits due to exhausting its wait attempts. It will be false
+ * in all the other cases.
+ *
+ * Returns true if remote_slot could catch up with the locally reserved
+ * position.
+ */
+static bool
+wait_for_primary_slot_catchup(WalReceiverConn *wrconn, RemoteSlot *remote_slot,
+ bool *wait_attempts_exceeded)
+{
+#define WAIT_OUTPUT_COLUMN_COUNT 4
+#define WAIT_PRIMARY_CATCHUP_ATTEMPTS 5
+
+ StringInfoData cmd;
+ int wait_count = 0;
+
+ Assert(wait_attempts_exceeded == NULL || *wait_attempts_exceeded == false);
+
+ ereport(LOG,
+ errmsg("waiting for remote slot \"%s\" LSN (%X/%X) and catalog xmin"
+ " (%u) to pass local slot LSN (%X/%X) and catalog xmin (%u)",
+ remote_slot->name,
+ LSN_FORMAT_ARGS(remote_slot->restart_lsn),
+ remote_slot->catalog_xmin,
+ LSN_FORMAT_ARGS(MyReplicationSlot->data.restart_lsn),
+ MyReplicationSlot->data.catalog_xmin));
+
+ initStringInfo(&cmd);
+ appendStringInfo(&cmd,
+ "SELECT conflict_reason IS NOT NULL, restart_lsn,"
+ " confirmed_flush_lsn, catalog_xmin"
+ " FROM pg_catalog.pg_replication_slots"
+ " WHERE slot_name = %s",
+ quote_literal_cstr(remote_slot->name));
+
+ for (;;)
+ {
+ bool new_invalidated;
+ XLogRecPtr new_restart_lsn;
+ XLogRecPtr new_confirmed_lsn;
+ TransactionId new_catalog_xmin;
+ WalRcvExecResult *res;
+ TupleTableSlot *tupslot;
+ int rc;
+ bool isnull;
+ Oid slotRow[WAIT_OUTPUT_COLUMN_COUNT] = {BOOLOID, LSNOID, LSNOID,
+ XIDOID};
+
+ /* Handle any termination request if any */
+ ProcessSlotSyncInterrupts(wrconn);
+
+ res = walrcv_exec(wrconn, cmd.data, WAIT_OUTPUT_COLUMN_COUNT, slotRow);
+
+ if (res->status != WALRCV_OK_TUPLES)
+ ereport(ERROR,
+ errmsg("could not fetch slot \"%s\" info from the"
+ " primary server: %s",
+ remote_slot->name, res->err));
+
+ tupslot = MakeSingleTupleTableSlot(res->tupledesc, &TTSOpsMinimalTuple);
+ if (!tuplestore_gettupleslot(res->tuplestore, true, false, tupslot))
+ {
+ ereport(WARNING,
+ errmsg("aborting initial sync for slot \"%s\"",
+ remote_slot->name),
+ errdetail("This slot was not found on the primary server."));
+ pfree(cmd.data);
+ walrcv_clear_result(res);
+
+ return false;
+ }
+
+ /*
+ * It is possible to get null value for restart_lsn if the slot is
+ * invalidated on the primary server, so handle accordingly.
+ */
+ new_invalidated = DatumGetBool(slot_getattr(tupslot, 1, &isnull));
+ Assert(!isnull);
+
+ new_restart_lsn = !slot_attisnull(tupslot, 2) ?
+ DatumGetLSN(slot_getattr(tupslot, 2, &isnull)) :
+ InvalidXLogRecPtr;
+
+ if (new_invalidated || XLogRecPtrIsInvalid(new_restart_lsn))
+ {
+ /*
+ * If the local-slot is in 'RS_EPHEMERAL' state, it will not be
+ * persisted in the caller and ReplicationSlotRelease() will drop
+ * it. But if the local slot is already persisted and has 'i'
+ * sync_state, then it will be marked as invalidated in the caller
+ * and next time onwards its sync will be skipped.
+ */
+ ereport(WARNING,
+ errmsg("aborting initial sync for slot \"%s\"",
+ remote_slot->name),
+ errdetail("This slot was invalidated on the primary server."));
+ pfree(cmd.data);
+ ExecClearTuple(tupslot);
+ walrcv_clear_result(res);
+
+ return false;
+ }
+
+ /*
+ * It is possible to get null values for confirmed_lsn and
+ * catalog_xmin if on the primary server the slot is just created with
+ * a valid restart_lsn and slot-sync worker has fetched the slot
+ * before the primary server could set valid confirmed_lsn and
+ * catalog_xmin.
+ */
+ new_confirmed_lsn = !slot_attisnull(tupslot, 3) ?
+ DatumGetLSN(slot_getattr(tupslot, 3, &isnull)) :
+ InvalidXLogRecPtr;
+
+ new_catalog_xmin = !slot_attisnull(tupslot, 4) ?
+ DatumGetTransactionId(slot_getattr(tupslot, 4, &isnull)) :
+ InvalidTransactionId;
+
+ ExecClearTuple(tupslot);
+ walrcv_clear_result(res);
+
+ if (new_restart_lsn >= MyReplicationSlot->data.restart_lsn &&
+ !XLogRecPtrIsInvalid(new_confirmed_lsn) &&
+ TransactionIdFollowsOrEquals(new_catalog_xmin,
+ MyReplicationSlot->data.catalog_xmin))
+ {
+ /* Update new values in remote_slot */
+ remote_slot->restart_lsn = new_restart_lsn;
+ remote_slot->confirmed_lsn = new_confirmed_lsn;
+ remote_slot->catalog_xmin = new_catalog_xmin;
+
+ ereport(LOG,
+ errmsg("wait over for remote slot \"%s\" as its LSN (%X/%X)"
+ " and catalog xmin (%u) has now passed local slot LSN"
+ " (%X/%X) and catalog xmin (%u)",
+ remote_slot->name,
+ LSN_FORMAT_ARGS(new_restart_lsn),
+ new_catalog_xmin,
+ LSN_FORMAT_ARGS(MyReplicationSlot->data.restart_lsn),
+ MyReplicationSlot->data.catalog_xmin));
+ pfree(cmd.data);
+
+ return true;
+ }
+
+ if (++wait_count >= WAIT_PRIMARY_CATCHUP_ATTEMPTS)
+ {
+ ereport(LOG,
+ errmsg("aborting the wait for remote slot \"%s\"",
+ remote_slot->name));
+ pfree(cmd.data);
+
+ if (wait_attempts_exceeded)
+ *wait_attempts_exceeded = true;
+
+ return false;
+ }
+
+ /*
+ * XXX: Is waiting for 2 seconds before retrying enough or more or
+ * less?
+ */
+ rc = WaitLatch(MyLatch,
+ WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+ 2000L,
+ WAIT_EVENT_REPL_SLOTSYNC_PRIMARY_CATCHUP);
+
+ if (rc & WL_LATCH_SET)
+ ResetLatch(MyLatch);
+ }
+}
+
+/*
+ * Update local slot metadata as per remote_slot's positions
+ */
+static void
+local_slot_update(RemoteSlot *remote_slot)
+{
+ Assert(MyReplicationSlot->data.invalidated == RS_INVAL_NONE);
+
+ LogicalConfirmReceivedLocation(remote_slot->confirmed_lsn);
+ LogicalIncreaseXminForSlot(remote_slot->confirmed_lsn,
+ remote_slot->catalog_xmin);
+ LogicalIncreaseRestartDecodingForSlot(remote_slot->confirmed_lsn,
+ remote_slot->restart_lsn);
+}
+
+/*
+ * Helper function for slotsync_drop_initiated_slots() and
+ * drop_obsolete_slots()
+ *
+ * Drops synced slot identified by the passed in name.
+ */
+static void
+drop_synced_slots_internal(const char *name, bool nowait)
+{
+ Assert(MyReplicationSlot == NULL);
+
+ ReplicationSlotAcquire(name, nowait);
+
+ Assert(MyReplicationSlot->data.sync_state != SYNCSLOT_STATE_NONE);
+
+ ReplicationSlotDropAcquired();
+}
+
+/*
+ * Drop the slots for which sync is initiated but not yet completed
+ * i.e. they are still waiting for the primary server to catch up (refer
+ * to the comment atop the file for details on this wait)
+ */
+void
+slotsync_drop_initiated_slots(void)
+{
+ List *local_slots = NIL;
+ ListCell *lc;
+
+ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
+
+ for (int i = 0; i < max_replication_slots; i++)
+ {
+ ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
+
+ if (s->in_use && s->data.sync_state == SYNCSLOT_STATE_INITIATED)
+ local_slots = lappend(local_slots, s);
+ }
+
+ LWLockRelease(ReplicationSlotControlLock);
+
+ foreach(lc, local_slots)
+ {
+ ReplicationSlot *s = (ReplicationSlot *) lfirst(lc);
+
+ drop_synced_slots_internal(NameStr(s->data.name), true);
+
+ ereport(LOG,
+ errmsg("dropped replication slot \"%s\" of dbid %d",
+ NameStr(s->data.name), s->data.database),
+ errdetail("It was not sync-ready."));
+ }
+
+ list_free(local_slots);
+}
+
+/*
+ * Get list of local logical slots which are synchronized from
+ * the primary server.
+ */
+static List *
+get_local_synced_slots(void)
+{
+ List *local_slots = NIL;
+
+ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
+
+ for (int i = 0; i < max_replication_slots; i++)
+ {
+ ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
+
+ /* Check if it is logical synchronized slot */
+ if (s->in_use && SlotIsLogical(s) &&
+ (s->data.sync_state != SYNCSLOT_STATE_NONE))
+ {
+ local_slots = lappend(local_slots, s);
+ }
+ }
+
+ LWLockRelease(ReplicationSlotControlLock);
+
+ return local_slots;
+}
+
+/*
+ * Helper function to check if local_slot is present in remote_slots list.
+ *
+ * It also checks if logical slot is locally invalidated i.e. invalidated on
+ * the standby but valid on the primary server. If found so, it sets
+ * locally_invalidated to true.
+ */
+static bool
+check_sync_slot_on_remote(ReplicationSlot *local_slot, List *remote_slots,
+ bool *locally_invalidated)
+{
+ ListCell *lc;
+
+ foreach(lc, remote_slots)
+ {
+ RemoteSlot *remote_slot = (RemoteSlot *) lfirst(lc);
+
+ if (strcmp(remote_slot->name, NameStr(local_slot->data.name)) == 0)
+ {
+ /*
+ * If remote slot is not invalidated but local slot is marked as
+ * invalidated, then set the bool.
+ */
+ SpinLockAcquire(&local_slot->mutex);
+ *locally_invalidated =
+ (remote_slot->invalidated == RS_INVAL_NONE) &&
+ (local_slot->data.invalidated != RS_INVAL_NONE);
+ SpinLockRelease(&local_slot->mutex);
+
+ return true;
+ }
+ }
+
+ return false;
+}
+
+/*
+ * Drop obsolete slots
+ *
+ * Drop the slots that no longer need to be synced i.e. these either do not
+ * exist on the primary or are no longer enabled for failover.
+ *
+ * Additionally, it drops slots that are valid on the primary but got
+ * invalidated on the standby. This situation may occur due to the following
+ * reasons:
+ * - The max_slot_wal_keep_size on the standby is insufficient to retain WAL
+ * records from the restart_lsn of the slot.
+ * - primary_slot_name is temporarily reset to null and the physical slot is
+ * removed.
+ * - The primary changes wal_level to a level lower than logical.
+ *
+ * The assumption is that these dropped slots will get recreated in next
+ * sync-cycle and it is okay to drop and recreate such slots as long as these
+ * are not consumable on the standby (which is the case currently).
+ */
+static void
+drop_obsolete_slots(List *remote_slot_list)
+{
+ List *local_slots = NIL;
+ ListCell *lc;
+
+ local_slots = get_local_synced_slots();
+
+ foreach(lc, local_slots)
+ {
+ ReplicationSlot *local_slot = (ReplicationSlot *) lfirst(lc);
+ bool remote_exists = false;
+ bool locally_invalidated = false;
+
+ remote_exists = check_sync_slot_on_remote(local_slot, remote_slot_list,
+ &locally_invalidated);
+
+ /*
+ * Drop the local slot either if it is not in the remote slots list or
+ * is invalidated while remote slot is still valid.
+ */
+ if (!remote_exists || locally_invalidated)
+ {
+ drop_synced_slots_internal(NameStr(local_slot->data.name), true);
+
+ ereport(LOG,
+ errmsg("dropped replication slot \"%s\" of dbid %d",
+ NameStr(local_slot->data.name),
+ local_slot->data.database));
+ }
+ }
+}
+
+/*
+ * Synchronize single slot to given position.
+ *
+ * This creates a new slot if there is no existing one and updates the
+ * metadata of the slot as per the data received from the primary server.
+ *
+ * The 'sync_state' in slot.data is set to SYNCSLOT_STATE_INITIATED
+ * immediately after creation. It stays in same state until the
+ * initialization is complete. The initialization is considered to
+ * be completed once the remote_slot catches up with locally reserved
+ * position and local slot is updated. The sync_state is then changed
+ * to SYNCSLOT_STATE_READY.
+ *
+ * Returns TRUE if the local slot is updated.
+ */
+static bool
+synchronize_one_slot(WalReceiverConn *wrconn, RemoteSlot *remote_slot)
+{
+ ReplicationSlot *slot;
+ bool slot_updated = false;
+
+ /*
+ * Sanity check: Make sure that concerned WAL is received before syncing
+ * slot to target lsn received from the primary server.
+ *
+ * This check should never pass as on the primary server, we have waited
+ * for the standby's confirmation before updating the logical slot.
+ */
+ SpinLockAcquire(&WalRcv->mutex);
+ if (remote_slot->confirmed_lsn > WalRcv->latestWalEnd)
+ {
+ SpinLockRelease(&WalRcv->mutex);
+ elog(ERROR, "exiting from slot synchronization as the received slot sync"
+ " LSN %X/%X for slot \"%s\" is ahead of the standby position %X/%X",
+ LSN_FORMAT_ARGS(remote_slot->confirmed_lsn),
+ remote_slot->name,
+ LSN_FORMAT_ARGS(WalRcv->latestWalEnd));
+ }
+ SpinLockRelease(&WalRcv->mutex);
+
+ /* Search for the named slot */
+ if ((slot = SearchNamedReplicationSlot(remote_slot->name, true)))
+ {
+ char sync_state;
+
+ SpinLockAcquire(&slot->mutex);
+ sync_state = slot->data.sync_state;
+ SpinLockRelease(&slot->mutex);
+
+ /* User created slot with the same name exists, raise ERROR. */
+ if (sync_state == SYNCSLOT_STATE_NONE)
+ ereport(ERROR,
+ errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("exiting from slot synchronization on receiving"
+ " the failover slot \"%s\" from the primary server",
+ remote_slot->name),
+ errdetail("A user-created slot with the same name already"
+ " exists on the standby."));
+
+ /*
+ * Slot created by the slot sync worker exists, sync it.
+ *
+ * It is important to acquire the slot here before checking
+ * invalidation. If we don't acquire the slot first, there could be a
+ * race condition that the local slot could be invalidated just after
+ * checking the 'invalidated' flag here and we could end up
+ * overwriting 'invalidated' flag to remote_slot's value. See
+ * InvalidatePossiblyObsoleteSlot() where it invalidates slot directly
+ * if the slot is not acquired by other processes.
+ */
+ ReplicationSlotAcquire(remote_slot->name, true);
+
+ Assert(slot == MyReplicationSlot);
+
+ /*
+ * Copy the invalidation cause from remote only if local slot is not
+ * invalidated locally, we don't want to overwrite existing one.
+ */
+ if (slot->data.invalidated == RS_INVAL_NONE)
+ {
+ SpinLockAcquire(&slot->mutex);
+ slot->data.invalidated = remote_slot->invalidated;
+ SpinLockRelease(&slot->mutex);
+
+ /* Make sure the invalidated state persists across server restart */
+ ReplicationSlotMarkDirty();
+ ReplicationSlotSave();
+ slot_updated = true;
+ }
+
+ /* Skip the sync of an invalidated slot */
+ if (slot->data.invalidated != RS_INVAL_NONE)
+ {
+ ReplicationSlotRelease();
+ return slot_updated;
+ }
+
+ /* Slot not ready yet, let's attempt to make it sync-ready now. */
+ if (sync_state == SYNCSLOT_STATE_INITIATED)
+ {
+ /*
+ * Wait for the primary server to catch-up. Refer to the comment
+ * atop the file for details on this wait.
+ */
+ if (remote_slot->restart_lsn < slot->data.restart_lsn ||
+ TransactionIdPrecedes(remote_slot->catalog_xmin,
+ slot->data.catalog_xmin))
+ {
+ if (!wait_for_primary_slot_catchup(wrconn, remote_slot, NULL))
+ {
+ ReplicationSlotRelease();
+ return false;
+ }
+ }
+
+ /*
+ * Wait for primary is over, update the lsns and mark the slot as
+ * READY for further syncs.
+ */
+ local_slot_update(remote_slot);
+ SpinLockAcquire(&slot->mutex);
+ slot->data.sync_state = SYNCSLOT_STATE_READY;
+ SpinLockRelease(&slot->mutex);
+
+ /* Make sure the slot changes persist across server restart */
+ ReplicationSlotMarkDirty();
+ ReplicationSlotSave();
+ slot_updated = true;
+
+ ereport(LOG,
+ errmsg("newly locally created slot \"%s\" is sync-ready now",
+ remote_slot->name));
+ }
+ /* Slot ready for sync, so sync it. */
+ else if (sync_state == SYNCSLOT_STATE_READY)
+ {
+ /*
+ * Sanity check: With hot_standby_feedback enabled and
+ * invalidations handled appropriately as above, this should never
+ * happen.
+ */
+ if (remote_slot->restart_lsn < slot->data.restart_lsn)
+ elog(ERROR,
+ "cannot synchronize local slot \"%s\" LSN(%X/%X)"
+ " to remote slot's LSN(%X/%X) as synchronization"
+ " would move it backwards", remote_slot->name,
+ LSN_FORMAT_ARGS(slot->data.restart_lsn),
+ LSN_FORMAT_ARGS(remote_slot->restart_lsn));
+
+ if (remote_slot->confirmed_lsn != slot->data.confirmed_flush ||
+ remote_slot->restart_lsn != slot->data.restart_lsn ||
+ remote_slot->catalog_xmin != slot->data.catalog_xmin)
+ {
+ /* Update LSN of slot to remote slot's current position */
+ local_slot_update(remote_slot);
+
+ /* Make sure the slot changes persist across server restart */
+ ReplicationSlotMarkDirty();
+ ReplicationSlotSave();
+ slot_updated = true;
+ }
+ }
+ }
+ /* Otherwise create the slot first. */
+ else
+ {
+ TransactionId xmin_horizon = InvalidTransactionId;
+
+ /* Skip creating the local slot if remote_slot is invalidated already */
+ if (remote_slot->invalidated != RS_INVAL_NONE)
+ return false;
+
+ /* Ensure that we have transaction env needed by get_database_oid() */
+ Assert(IsTransactionState());
+
+ ReplicationSlotCreate(remote_slot->name, true, RS_EPHEMERAL,
+ remote_slot->two_phase,
+ remote_slot->failover,
+ SYNCSLOT_STATE_INITIATED);
+
+ /* For shorter lines. */
+ slot = MyReplicationSlot;
+
+ SpinLockAcquire(&slot->mutex);
+ slot->data.database = get_database_oid(remote_slot->database, false);
+ namestrcpy(&slot->data.plugin, remote_slot->plugin);
+ SpinLockRelease(&slot->mutex);
+
+ ReplicationSlotReserveWal();
+
+ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
+ xmin_horizon = GetOldestSafeDecodingTransactionId(true);
+ SpinLockAcquire(&slot->mutex);
+ slot->effective_catalog_xmin = xmin_horizon;
+ slot->data.catalog_xmin = xmin_horizon;
+ SpinLockRelease(&slot->mutex);
+ ReplicationSlotsComputeRequiredXmin(true);
+ LWLockRelease(ProcArrayLock);
+
+ /*
+ * Wait for the primary server to catch-up. Refer to the comment atop
+ * the file for details on this wait.
+ *
+ * We also need to wait until remote_slot's confirmed_lsn becomes
+ * valid. It is possible to get null values for confirmed_lsn and
+ * catalog_xmin if on the primary server the slot is just created with
+ * a valid restart_lsn and slot-sync worker has fetched the slot
+ * before the primary server could set valid confirmed_lsn and
+ * catalog_xmin.
+ */
+ if (remote_slot->restart_lsn < slot->data.restart_lsn ||
+ XLogRecPtrIsInvalid(remote_slot->confirmed_lsn) ||
+ TransactionIdPrecedes(remote_slot->catalog_xmin,
+ slot->data.catalog_xmin))
+ {
+ bool wait_attempts_exceeded = false;
+
+ if (!wait_for_primary_slot_catchup(wrconn, remote_slot, &wait_attempts_exceeded))
+ {
+ /*
+ * The remote slot didn't catch up to locally reserved
+ * position.
+ *
+ * We do not drop the slot because the restart_lsn can be
+ * ahead of the current location when recreating the slot in
+ * the next cycle. It may take more time to create such a
+ * slot. Therefore, we persist it (provided remote-slot is
+ * still valid i.e wait_attempts_exceeded is true) and attempt
+ * the wait and synchronization in the next cycle.
+ */
+ if (wait_attempts_exceeded)
+ {
+ ReplicationSlotPersist();
+ slot_updated = true;
+ }
+
+ ReplicationSlotRelease();
+ return slot_updated;
+ }
+ }
+
+ /*
+ * Wait for primary is either not needed or is over. Update the lsns
+ * and mark the slot as READY for further syncs.
+ */
+ local_slot_update(remote_slot);
+ SpinLockAcquire(&slot->mutex);
+ slot->data.sync_state = SYNCSLOT_STATE_READY;
+ SpinLockRelease(&slot->mutex);
+
+ /* Mark the slot as PERSISTENT and save the changes to disk */
+ ReplicationSlotPersist();
+ slot_updated = true;
+
+ ereport(LOG,
+ errmsg("newly locally created slot \"%s\" is sync-ready now",
+ remote_slot->name));
+ }
+
+ ReplicationSlotRelease();
+
+ return slot_updated;
+}
+
+/*
+ * Maps the pg_replication_slots.conflict_reason text value to
+ * ReplicationSlotInvalidationCause enum value
+ */
+static ReplicationSlotInvalidationCause
+get_slot_invalidation_cause(char *conflict_reason)
+{
+ Assert(conflict_reason);
+
+ if (strcmp(conflict_reason, SLOT_INVAL_WAL_REMOVED_TEXT) == 0)
+ return RS_INVAL_WAL_REMOVED;
+
+ if (strcmp(conflict_reason, SLOT_INVAL_HORIZON_TEXT) == 0)
+ return RS_INVAL_HORIZON;
+
+ if (strcmp(conflict_reason, SLOT_INVAL_WAL_LEVEL_TEXT) == 0)
+ return RS_INVAL_WAL_LEVEL;
+
+ /* Cannot get here */
+ Assert(0);
+}
+
+/*
+ * Synchronize slots.
+ *
+ * Gets the failover logical slots info from the primary server and updates
+ * the slots locally. Creates the slots if not present on the standby.
+ *
+ * Returns TRUE if any of the slots gets updated in this sync-cycle.
+ */
+static bool
+synchronize_slots(WalReceiverConn *wrconn)
+{
+#define SLOTSYNC_COLUMN_COUNT 9
+ Oid slotRow[SLOTSYNC_COLUMN_COUNT] = {TEXTOID, TEXTOID, LSNOID,
+ LSNOID, XIDOID, BOOLOID, BOOLOID, TEXTOID, TEXTOID};
+
+ WalRcvExecResult *res;
+ TupleTableSlot *tupslot;
+ StringInfoData s;
+ List *remote_slot_list = NIL;
+ ListCell *lc;
+ bool some_slot_updated = false;
+
+ /* WalRcv shared memory not set yet */
+ if (!WalRcv)
+ return false;
+
+ /*
+ * The primary_slot_name is not set yet or WALs not received yet.
+ * Synchronization is not possible if the walreceiver is not started.
+ */
+ SpinLockAcquire(&WalRcv->mutex);
+ if ((WalRcv->slotname[0] == '\0') ||
+ XLogRecPtrIsInvalid(WalRcv->latestWalEnd))
+ {
+ SpinLockRelease(&WalRcv->mutex);
+ return false;
+ }
+ SpinLockRelease(&WalRcv->mutex);
+
+ /* The syscache access in walrcv_exec() needs a transaction env. */
+ StartTransactionCommand();
+
+ initStringInfo(&s);
+
+ /* Construct query to fetch slots with failover enabled. */
+ appendStringInfo(&s,
+ "SELECT slot_name, plugin, confirmed_flush_lsn,"
+ " restart_lsn, catalog_xmin, two_phase, failover,"
+ " database, conflict_reason"
+ " FROM pg_catalog.pg_replication_slots"
+ " WHERE failover");
+
+ /* Execute the query */
+ res = walrcv_exec(wrconn, s.data, SLOTSYNC_COLUMN_COUNT, slotRow);
+ pfree(s.data);
+
+ if (res->status != WALRCV_OK_TUPLES)
+ ereport(ERROR,
+ errmsg("could not fetch failover logical slots info"
+ " from the primary server: %s", res->err));
+
+
+ /* Construct the remote_slot tuple and synchronize each slot locally */
+ tupslot = MakeSingleTupleTableSlot(res->tupledesc, &TTSOpsMinimalTuple);
+ while (tuplestore_gettupleslot(res->tuplestore, true, false, tupslot))
+ {
+ bool isnull;
+ RemoteSlot *remote_slot = palloc0(sizeof(RemoteSlot));
+
+ remote_slot->name = TextDatumGetCString(slot_getattr(tupslot, 1, &isnull));
+ Assert(!isnull);
+
+ remote_slot->plugin = TextDatumGetCString(slot_getattr(tupslot, 2, &isnull));
+ Assert(!isnull);
+
+ /*
+ * It is possible to get null values for LSN and Xmin if slot is
+ * invalidated on the primary server, so handle accordingly.
+ */
+ remote_slot->confirmed_lsn = !slot_attisnull(tupslot, 3) ?
+ DatumGetLSN(slot_getattr(tupslot, 3, &isnull)) :
+ InvalidXLogRecPtr;
+
+ remote_slot->restart_lsn = !slot_attisnull(tupslot, 4) ?
+ DatumGetLSN(slot_getattr(tupslot, 4, &isnull)) :
+ InvalidXLogRecPtr;
+
+ remote_slot->catalog_xmin = !slot_attisnull(tupslot, 5) ?
+ DatumGetTransactionId(slot_getattr(tupslot, 5, &isnull)) :
+ InvalidTransactionId;
+
+ remote_slot->two_phase = DatumGetBool(slot_getattr(tupslot, 6, &isnull));
+ Assert(!isnull);
+
+ remote_slot->failover = DatumGetBool(slot_getattr(tupslot, 7, &isnull));
+ Assert(!isnull);
+
+ remote_slot->database = TextDatumGetCString(slot_getattr(tupslot,
+ 8, &isnull));
+ Assert(!isnull);
+
+ remote_slot->invalidated = !slot_attisnull(tupslot, 9) ?
+ get_slot_invalidation_cause(TextDatumGetCString(slot_getattr(tupslot, 9, &isnull))) :
+ RS_INVAL_NONE;
+
+ /* Create list of remote slots */
+ remote_slot_list = lappend(remote_slot_list, remote_slot);
+
+ ExecClearTuple(tupslot);
+ }
+
+ /* Drop local slots that no longer need to be synced. */
+ drop_obsolete_slots(remote_slot_list);
+
+ /* Now sync the slots locally */
+ foreach(lc, remote_slot_list)
+ {
+ RemoteSlot *remote_slot = (RemoteSlot *) lfirst(lc);
+
+ some_slot_updated |= synchronize_one_slot(wrconn, remote_slot);
+ }
+
+ /* We are done, free remote_slot_list elements */
+ list_free_deep(remote_slot_list);
+
+ walrcv_clear_result(res);
+
+ CommitTransactionCommand();
+
+ return some_slot_updated;
+}
+
+/*
+ * Checks the primary server info.
+ *
+ * Using the specified primary server connection, check whether we are a
+ * cascading standby. It also validates primary_slot_name for non-cascading
+ * standbys.
+ */
+static void
+check_primary_info(WalReceiverConn *wrconn, bool *am_cascading_standby)
+{
+#define PRIMARY_INFO_OUTPUT_COL_COUNT 2
+ WalRcvExecResult *res;
+ Oid slotRow[PRIMARY_INFO_OUTPUT_COL_COUNT] = {BOOLOID, BOOLOID};
+ StringInfoData cmd;
+ bool isnull;
+ TupleTableSlot *tupslot;
+ bool valid;
+ bool remote_in_recovery;
+ bool tuple_ok PG_USED_FOR_ASSERTS_ONLY;
+
+ /* The syscache access in walrcv_exec() needs a transaction env. */
+ StartTransactionCommand();
+
+ Assert(am_cascading_standby != NULL);
+
+ *am_cascading_standby = false; /* overwritten later if cascading */
+
+ initStringInfo(&cmd);
+ appendStringInfo(&cmd,
+ "SELECT pg_is_in_recovery(), count(*) = 1"
+ " FROM pg_replication_slots"
+ " WHERE slot_type='physical' AND slot_name=%s",
+ quote_literal_cstr(PrimarySlotName));
+
+ res = walrcv_exec(wrconn, cmd.data, PRIMARY_INFO_OUTPUT_COL_COUNT, slotRow);
+ pfree(cmd.data);
+
+ if (res->status != WALRCV_OK_TUPLES)
+ ereport(ERROR,
+ errmsg("could not fetch primary_slot_name \"%s\" info from the"
+ " primary server: %s", PrimarySlotName, res->err));
+
+ tupslot = MakeSingleTupleTableSlot(res->tupledesc, &TTSOpsMinimalTuple);
+ tuple_ok = tuplestore_gettupleslot(res->tuplestore, true, false, tupslot);
+ Assert(tuple_ok); /* It must return one tuple */
+
+ remote_in_recovery = DatumGetBool(slot_getattr(tupslot, 1, &isnull));
+ Assert(!isnull);
+
+ if (remote_in_recovery)
+ {
+ /* No need to check further, return that we are cascading standby */
+ *am_cascading_standby = true;
+ }
+ else
+ {
+ /* We are a normal standby. */
+ valid = DatumGetBool(slot_getattr(tupslot, 2, &isnull));
+ Assert(!isnull);
+
+ if (!valid)
+ ereport(ERROR,
+ errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ /* translator: second %s is a GUC variable name */
+ errdetail("The primary server slot \"%s\" specified by %s is not valid.",
+ PrimarySlotName, "primary_slot_name"));
+ }
+
+ ExecClearTuple(tupslot);
+ walrcv_clear_result(res);
+ CommitTransactionCommand();
+}
+
+/*
+ * Check that all necessary GUCs for slot synchronization are set
+ * appropriately. If not, raise an ERROR.
+ */
+static void
+validate_slotsync_parameters(char **dbname)
+{
+ /* Sanity check. */
+ Assert(enable_syncslot);
+
+ /*
+ * A physical replication slot(primary_slot_name) is required on the
+ * primary to ensure that the rows needed by the standby are not removed
+ * after restarting, so that the synchronized slot on the standby will not
+ * be invalidated.
+ */
+ if (PrimarySlotName == NULL || strcmp(PrimarySlotName, "") == 0)
+ ereport(ERROR,
+ /* translator: %s is a GUC variable name */
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ errhint("%s must be defined.", "primary_slot_name"));
+
+ /*
+ * Hot_standby_feedback must be enabled to cooperate with the physical
+ * replication slot, which allows informing the primary about the xmin and
+ * catalog_xmin values on the standby.
+ */
+ if (!hot_standby_feedback)
+ ereport(ERROR,
+ /* translator: %s is a GUC variable name */
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ errhint("%s must be enabled.", "hot_standby_feedback"));
+
+ /*
+ * Logical decoding requires wal_level >= logical and we currently only
+ * synchronize logical slots.
+ */
+ if (wal_level < WAL_LEVEL_LOGICAL)
+ ereport(ERROR,
+ /* translator: %s is a GUC variable name */
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ errhint("wal_level must be >= logical."));
+
+ /*
+ * The primary_conninfo is required to make connection to primary for
+ * getting slots information.
+ */
+ if (PrimaryConnInfo == NULL || strcmp(PrimaryConnInfo, "") == 0)
+ ereport(ERROR,
+ /* translator: %s is a GUC variable name */
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ errhint("%s must be defined.", "primary_conninfo"));
+
+ /*
+ * The slot sync worker needs a database connection for walrcv_exec to
+ * work.
+ */
+ *dbname = walrcv_get_dbname_from_conninfo(PrimaryConnInfo);
+ if (*dbname == NULL)
+ ereport(ERROR,
+
+ /*
+ * translator: 'dbname' is a specific option; %s is a GUC variable
+ * name
+ */
+ errmsg("exiting from slot synchronization due to bad configuration"),
+ errhint("'dbname' must be specified in %s.", "primary_conninfo"));
+}
+
+/*
+ * Re-read the config file.
+ *
+ * If any of the slot sync GUCs have changed, exit the worker and
+ * let it get restarted by the postmaster.
+ */
+static void
+slotsync_reread_config(WalReceiverConn *wrconn)
+{
+ char *old_primary_conninfo = pstrdup(PrimaryConnInfo);
+ char *old_primary_slotname = pstrdup(PrimarySlotName);
+ bool old_hot_standby_feedback = hot_standby_feedback;
+ bool conninfo_changed;
+ bool primary_slotname_changed;
+
+ ConfigReloadPending = false;
+ ProcessConfigFile(PGC_SIGHUP);
+
+ conninfo_changed = strcmp(old_primary_conninfo, PrimaryConnInfo) != 0;
+ primary_slotname_changed = strcmp(old_primary_slotname, PrimarySlotName) != 0;
+
+ if (conninfo_changed ||
+ primary_slotname_changed ||
+ (old_hot_standby_feedback != hot_standby_feedback))
+ {
+ ereport(LOG,
+ errmsg("slot sync worker will restart because of"
+ " a parameter change"));
+ /* The exit code 1 will make postmaster restart this worker */
+ proc_exit(1);
+ }
+
+ pfree(old_primary_conninfo);
+ pfree(old_primary_slotname);
+}
+
+/*
+ * Interrupt handler for main loop of slot sync worker.
+ */
+static void
+ProcessSlotSyncInterrupts(WalReceiverConn *wrconn)
+{
+ CHECK_FOR_INTERRUPTS();
+
+ if (ShutdownRequestPending)
+ {
+ walrcv_disconnect(wrconn);
+ ereport(LOG,
+ errmsg("replication slot sync worker is shutting down"
+ " on receiving SIGINT"));
+ proc_exit(0);
+ }
+
+ if (ConfigReloadPending)
+ slotsync_reread_config(wrconn);
+}
+
+/*
+ * Cleanup function for logical replication launcher.
+ *
+ * Called on logical replication launcher exit.
+ */
+static void
+slotsync_worker_onexit(int code, Datum arg)
+{
+ SpinLockAcquire(&SlotSyncWorker->mutex);
+ SlotSyncWorker->pid = InvalidPid;
+ SpinLockRelease(&SlotSyncWorker->mutex);
+}
+
+/*
+ * The main loop of our worker process.
+ *
+ * It connects to the primary server, fetches logical failover slots
+ * information periodically in order to create and sync the slots.
+ */
+void
+ReplSlotSyncWorkerMain(Datum main_arg)
+{
+ WalReceiverConn *wrconn = NULL;
+ char *dbname;
+ bool am_cascading_standby;
+ char *err;
+
+ ereport(LOG, errmsg("replication slot sync worker started"));
+
+ on_shmem_exit(slotsync_worker_onexit, (Datum) 0);
+
+ SpinLockAcquire(&SlotSyncWorker->mutex);
+
+ Assert(SlotSyncWorker->pid == InvalidPid);
+
+ /* Advertise our PID so that the startup process can kill us on promotion */
+ SlotSyncWorker->pid = MyProcPid;
+
+ SpinLockRelease(&SlotSyncWorker->mutex);
+
+ /* Setup signal handling */
+ pqsignal(SIGHUP, SignalHandlerForConfigReload);
+ pqsignal(SIGINT, SignalHandlerForShutdownRequest);
+ pqsignal(SIGTERM, die);
+ BackgroundWorkerUnblockSignals();
+
+ /* Load the libpq-specific functions */
+ load_file("libpqwalreceiver", false);
+
+ validate_slotsync_parameters(&dbname);
+
+ /*
+ * Connect to the database specified by user in primary_conninfo. We need
+ * a database connection for walrcv_exec to work. Please see comments atop
+ * libpqrcv_exec.
+ */
+ BackgroundWorkerInitializeConnection(dbname, NULL, 0);
+
+ /*
+ * Establish the connection to the primary server for slots
+ * synchronization.
+ */
+ wrconn = walrcv_connect(PrimaryConnInfo, true, false,
+ cluster_name[0] ? cluster_name : "slotsyncworker",
+ &err);
+ if (wrconn == NULL)
+ ereport(ERROR,
+ errcode(ERRCODE_CONNECTION_FAILURE),
+ errmsg("could not connect to the primary server: %s", err));
+
+ /*
+ * Using the specified primary server connection, check whether we are
+ * cascading standby and validates primary_slot_name for
+ * non-cascading-standbys.
+ */
+ check_primary_info(wrconn, &am_cascading_standby);
+
+ /* Main wait loop. */
+ for (;;)
+ {
+ int rc;
+ long naptime = WORKER_DEFAULT_NAPTIME_MS;
+ TimestampTz now;
+ bool some_slot_updated;
+
+ ProcessSlotSyncInterrupts(wrconn);
+
+ if (am_cascading_standby)
+ {
+ /*
+ * Slot synchronization is currently not supported on cascading
+ * standby. So if we are on the cascading standby, skip the sync
+ * and take a longer nap before we check again whether we are
+ * still cascading standby or not.
+ */
+ naptime = 6 * WORKER_INACTIVITY_NAPTIME_MS; /* 60 sec */
+ }
+ else
+ {
+ some_slot_updated = synchronize_slots(wrconn);
+
+ /*
+ * If any of the slots get updated in this sync-cycle, use default
+ * naptime and update 'last_update_time'. But if no activity is
+ * observed in this sync-cycle, then increase naptime provided
+ * inactivity time reaches threshold.
+ */
+ now = GetCurrentTimestamp();
+ if (some_slot_updated)
+ last_update_time = now;
+ else if (TimestampDifferenceExceeds(last_update_time,
+ now, WORKER_INACTIVITY_THRESHOLD_MS))
+ naptime = WORKER_INACTIVITY_NAPTIME_MS;
+ }
+
+ rc = WaitLatch(MyLatch,
+ WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+ naptime,
+ WAIT_EVENT_REPL_SLOTSYNC_MAIN);
+
+ if (rc & WL_LATCH_SET)
+ ResetLatch(MyLatch);
+
+ /*
+ * If the standby was promoted then what was previously a cascading
+ * standby might no longer be one, so recheck each time.
+ */
+ if (am_cascading_standby)
+ check_primary_info(wrconn, &am_cascading_standby);
+ }
+
+ /*
+ * The slot sync worker can not get here because it will only stop when it
+ * receives a SIGINT from the logical replication launcher, or when there
+ * is an error.
+ */
+ Assert(false);
+}
+
+/*
+ * Is current process the slot sync worker?
+ */
+bool
+IsLogicalSlotSyncWorker(void)
+{
+ return SlotSyncWorker->pid == MyProcPid;
+}
+
+/*
+ * Shut down the slot sync worker.
+ */
+void
+ShutDownSlotSync(void)
+{
+ SpinLockAcquire(&SlotSyncWorker->mutex);
+ if (SlotSyncWorker->pid == InvalidPid)
+ {
+ SpinLockRelease(&SlotSyncWorker->mutex);
+ return;
+ }
+
+ kill(SlotSyncWorker->pid, SIGINT);
+
+ SpinLockRelease(&SlotSyncWorker->mutex);
+
+ /* Wait for it to die. */
+ for (;;)
+ {
+ int rc;
+
+ /* Wait a bit, we don't expect to have to wait long. */
+ rc = WaitLatch(MyLatch,
+ WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+ 10L, WAIT_EVENT_BGWORKER_SHUTDOWN);
+
+ if (rc & WL_LATCH_SET)
+ {
+ ResetLatch(MyLatch);
+ CHECK_FOR_INTERRUPTS();
+ }
+
+ SpinLockAcquire(&SlotSyncWorker->mutex);
+
+ /* Is it gone? */
+ if (SlotSyncWorker->pid == InvalidPid)
+ break;
+
+ SpinLockRelease(&SlotSyncWorker->mutex);
+ }
+
+ SpinLockRelease(&SlotSyncWorker->mutex);
+}
+
+/*
+ * Allocate and initialize slot sync worker shared memory
+ */
+void
+SlotSyncWorkerShmemInit(void)
+{
+ Size size;
+ bool found;
+
+ size = sizeof(SlotSyncWorkerCtxStruct);
+ size = MAXALIGN(size);
+
+ SlotSyncWorker = (SlotSyncWorkerCtxStruct *)
+ ShmemInitStruct("Slot Sync Worker Data", size, &found);
+
+ if (!found)
+ {
+ memset(SlotSyncWorker, 0, size);
+ SlotSyncWorker->pid = InvalidPid;
+ SpinLockInit(&SlotSyncWorker->mutex);
+ }
+}
+
+/*
+ * Register the background worker for slots synchronization provided
+ * enable_syncslot is ON.
+ */
+void
+SlotSyncWorkerRegister(void)
+{
+ BackgroundWorker bgw;
+
+ if (!enable_syncslot)
+ {
+ ereport(LOG,
+ errmsg("skipping slot synchronization"),
+ errdetail("enable_syncslot is disabled."));
+ return;
+ }
+
+ memset(&bgw, 0, sizeof(bgw));
+
+ /* We need database connection which needs shared-memory access as well. */
+ bgw.bgw_flags = BGWORKER_SHMEM_ACCESS |
+ BGWORKER_BACKEND_DATABASE_CONNECTION;
+
+ /* Start as soon as a consistent state has been reached in a hot standby */
+ bgw.bgw_start_time = BgWorkerStart_ConsistentState_HotStandby;
+
+ snprintf(bgw.bgw_library_name, MAXPGPATH, "postgres");
+ snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ReplSlotSyncWorkerMain");
+ snprintf(bgw.bgw_name, BGW_MAXLEN,
+ "replication slot sync worker");
+ snprintf(bgw.bgw_type, BGW_MAXLEN,
+ "slot sync worker");
+
+ bgw.bgw_restart_time = BGW_DEFAULT_RESTART_INTERVAL;
+ bgw.bgw_notify_pid = 0;
+ bgw.bgw_main_arg = (Datum) 0;
+
+ RegisterBackgroundWorker(&bgw);
+}
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 3fe1f9953b..287412e1a6 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -141,7 +141,20 @@
* subscribe to the new primary without losing any data.
*
* However, we do not enable failover for slots created by the table sync
- * worker.
+ * worker. This is because the table sync slot might not be fully synced on the
+ * standby due to the following reasons:
+ *
+ * - The standby needs to wait for the primary server to catch up because the
+ * local restart_lsn of the newly created slot on the standby is set using
+ * the latest redo position (GetXLogReplayRecPtr()), which is typically ahead
+ * of the primary's restart_lsn.
+ * - The table sync slot's restart_lsn won't be advanced until the state
+ * becomes SUBREL_STATE_CATCHUP.
+ *
+ * Therefore, if a failover happens before the restart_lsn advances, the table
+ * sync slot will not be synced to the standby. Consequently, we will not be
+ * able to subscribe to the promoted standby due to the absence of the
+ * necessary table sync slot.
*
* Additionally, failover is not enabled for the main slot if the table sync is
* in progress. This is because if a failover occurs while the table sync
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 696376400e..9d27593979 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -47,6 +47,7 @@
#include "miscadmin.h"
#include "pgstat.h"
#include "replication/slot.h"
+#include "replication/walsender.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/proc.h"
@@ -103,7 +104,6 @@ int max_replication_slots = 10; /* the maximum number of replication
* slots */
static void ReplicationSlotShmemExit(int code, Datum arg);
-static void ReplicationSlotDropAcquired(void);
static void ReplicationSlotDropPtr(ReplicationSlot *slot);
/* internal persistency functions */
@@ -250,16 +250,22 @@ ReplicationSlotValidateName(const char *name, int elevel)
* user will only get commit prepared.
* failover: If enabled, allows the slot to be synced to physical standbys so
* that logical replication can be resumed after failover.
+ * sync_state: Defines slot synchronization state. This function is expected
+ * to receive either SYNCSLOT_STATE_NONE for the user created slots or
+ * SYNCSLOT_STATE_INITIATED for the slots being synchronized on the physical
+ * standby.
*/
void
ReplicationSlotCreate(const char *name, bool db_specific,
ReplicationSlotPersistency persistency,
- bool two_phase, bool failover)
+ bool two_phase, bool failover, char sync_state)
{
ReplicationSlot *slot = NULL;
int i;
Assert(MyReplicationSlot == NULL);
+ Assert(sync_state == SYNCSLOT_STATE_NONE ||
+ sync_state == SYNCSLOT_STATE_INITIATED);
ReplicationSlotValidateName(name, ERROR);
@@ -315,6 +321,7 @@ ReplicationSlotCreate(const char *name, bool db_specific,
slot->data.two_phase = two_phase;
slot->data.two_phase_at = InvalidXLogRecPtr;
slot->data.failover = failover;
+ slot->data.sync_state = sync_state;
/* and then data only present in shared memory */
slot->just_dirtied = false;
@@ -680,6 +687,17 @@ ReplicationSlotDrop(const char *name, bool nowait)
ReplicationSlotAcquire(name, nowait);
+ /*
+ * Do not allow users to drop the slots which are currently being synced
+ * from the primary to the standby.
+ */
+ if (RecoveryInProgress() &&
+ MyReplicationSlot->data.sync_state != SYNCSLOT_STATE_NONE)
+ ereport(ERROR,
+ errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot drop replication slot \"%s\"", name),
+ errdetail("This slot is being synced from the primary server."));
+
ReplicationSlotDropAcquired();
}
@@ -699,6 +717,17 @@ ReplicationSlotAlter(const char *name, bool failover)
errmsg("cannot use %s with a physical replication slot",
"ALTER_REPLICATION_SLOT"));
+ /*
+ * Do not allow users to alter the slots which are currently being synced
+ * from the primary to the standby.
+ */
+ if (RecoveryInProgress() &&
+ MyReplicationSlot->data.sync_state != SYNCSLOT_STATE_NONE)
+ ereport(ERROR,
+ errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+ errmsg("cannot alter replication slot \"%s\"", name),
+ errdetail("This slot is being synced from the primary server."));
+
SpinLockAcquire(&MyReplicationSlot->mutex);
MyReplicationSlot->data.failover = failover;
SpinLockRelease(&MyReplicationSlot->mutex);
@@ -711,7 +740,7 @@ ReplicationSlotAlter(const char *name, bool failover)
/*
* Permanently drop the currently acquired replication slot.
*/
-static void
+void
ReplicationSlotDropAcquired(void)
{
ReplicationSlot *slot = MyReplicationSlot;
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index eb685089b3..b59d6e62fd 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -43,7 +43,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve,
/* acquire replication slot, this will check for conflicting names */
ReplicationSlotCreate(name, false,
temporary ? RS_TEMPORARY : RS_PERSISTENT, false,
- false);
+ false, SYNCSLOT_STATE_NONE);
if (immediately_reserve)
{
@@ -136,7 +136,7 @@ create_logical_replication_slot(char *name, char *plugin,
*/
ReplicationSlotCreate(name, true,
temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase,
- failover);
+ failover, SYNCSLOT_STATE_NONE);
/*
* Create logical decoding context to find start point or, if we don't
@@ -237,7 +237,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS)
Datum
pg_get_replication_slots(PG_FUNCTION_ARGS)
{
-#define PG_GET_REPLICATION_SLOTS_COLS 16
+#define PG_GET_REPLICATION_SLOTS_COLS 17
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
XLogRecPtr currlsn;
int slotno;
@@ -418,21 +418,36 @@ pg_get_replication_slots(PG_FUNCTION_ARGS)
break;
case RS_INVAL_WAL_REMOVED:
- values[i++] = CStringGetTextDatum("wal_removed");
+ values[i++] = CStringGetTextDatum(SLOT_INVAL_WAL_REMOVED_TEXT);
break;
case RS_INVAL_HORIZON:
- values[i++] = CStringGetTextDatum("rows_removed");
+ values[i++] = CStringGetTextDatum(SLOT_INVAL_HORIZON_TEXT);
break;
case RS_INVAL_WAL_LEVEL:
- values[i++] = CStringGetTextDatum("wal_level_insufficient");
+ values[i++] = CStringGetTextDatum(SLOT_INVAL_WAL_LEVEL_TEXT);
break;
}
}
values[i++] = BoolGetDatum(slot_contents.data.failover);
+ switch (slot_contents.data.sync_state)
+ {
+ case SYNCSLOT_STATE_NONE:
+ values[i++] = CStringGetTextDatum("none");
+ break;
+
+ case SYNCSLOT_STATE_INITIATED:
+ values[i++] = CStringGetTextDatum("initiated");
+ break;
+
+ case SYNCSLOT_STATE_READY:
+ values[i++] = CStringGetTextDatum("ready");
+ break;
+ }
+
Assert(i == PG_GET_REPLICATION_SLOTS_COLS);
tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 58165ea614..9d8710f904 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1224,7 +1224,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
{
ReplicationSlotCreate(cmd->slotname, false,
cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT,
- false, false);
+ false, false, SYNCSLOT_STATE_NONE);
if (reserve_wal)
{
@@ -1255,7 +1255,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
*/
ReplicationSlotCreate(cmd->slotname, true,
cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL,
- two_phase, failover);
+ two_phase, failover, SYNCSLOT_STATE_NONE);
/*
* Do options check early so that we can bail before calling the
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index e5119ed55d..04fed1007e 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -38,6 +38,7 @@
#include "replication/slot.h"
#include "replication/walreceiver.h"
#include "replication/walsender.h"
+#include "replication/worker_internal.h"
#include "storage/bufmgr.h"
#include "storage/dsm.h"
#include "storage/ipc.h"
@@ -342,6 +343,7 @@ CreateOrAttachShmemStructs(void)
WalSummarizerShmemInit();
PgArchShmemInit();
ApplyLauncherShmemInit();
+ SlotSyncWorkerShmemInit();
/*
* Set up other modules that need some shared memory space
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 1eaaf3c6c5..19b08c1b5f 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3286,6 +3286,17 @@ ProcessInterrupts(void)
*/
proc_exit(1);
}
+ else if (IsLogicalSlotSyncWorker())
+ {
+ elog(DEBUG1,
+ "replication slot sync worker is shutting down due to administrator command");
+
+ /*
+ * Slot sync worker can be stopped at any time. Use exit status 1
+ * so the background worker is restarted.
+ */
+ proc_exit(1);
+ }
else if (IsBackgroundWorker)
ereport(FATAL,
(errcode(ERRCODE_ADMIN_SHUTDOWN),
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 088eb977d4..aee5fe7315 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -53,6 +53,8 @@ LOGICAL_APPLY_MAIN "Waiting in main loop of logical replication apply process."
LOGICAL_LAUNCHER_MAIN "Waiting in main loop of logical replication launcher process."
LOGICAL_PARALLEL_APPLY_MAIN "Waiting in main loop of logical replication parallel apply process."
RECOVERY_WAL_STREAM "Waiting in main loop of startup process for WAL to arrive, during streaming recovery."
+REPL_SLOTSYNC_MAIN "Waiting in main loop of slot sync worker."
+REPL_SLOTSYNC_PRIMARY_CATCHUP "Waiting for the primary to catch-up, in slot sync worker."
SYSLOGGER_MAIN "Waiting in main loop of syslogger process."
WAL_RECEIVER_MAIN "Waiting in main loop of WAL receiver process."
WAL_SENDER_MAIN "Waiting in main loop of WAL sender process."
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index e53ebc6dc2..0f5ec63de1 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -68,6 +68,7 @@
#include "replication/logicallauncher.h"
#include "replication/slot.h"
#include "replication/syncrep.h"
+#include "replication/worker_internal.h"
#include "storage/bufmgr.h"
#include "storage/large_object.h"
#include "storage/pg_shmem.h"
@@ -2044,6 +2045,15 @@ struct config_bool ConfigureNamesBool[] =
NULL, NULL, NULL
},
+ {
+ {"enable_syncslot", PGC_POSTMASTER, REPLICATION_STANDBY,
+ gettext_noop("Enables a physical standby to synchronize logical failover slots from the primary server."),
+ },
+ &enable_syncslot,
+ false,
+ NULL, NULL, NULL
+ },
+
/* End-of-list marker */
{
{NULL, 0, 0, NULL, NULL}, NULL, false, NULL, NULL, NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index b2809c711a..136be912e6 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -361,6 +361,7 @@
#wal_retrieve_retry_interval = 5s # time to wait before retrying to
# retrieve WAL after a failed attempt
#recovery_min_apply_delay = 0 # minimum delay for applying changes during recovery
+#enable_syncslot = off # enables slot synchronization on the physical standby from the primary
# - Subscribers -
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index f40726c4f7..d7c9fe31f8 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11115,9 +11115,9 @@
proname => 'pg_get_replication_slots', prorows => '10', proisstrict => 'f',
proretset => 't', provolatile => 's', prorettype => 'record',
proargtypes => '',
- proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text,bool}',
- proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
- proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflict_reason,failover}',
+ proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text,bool,text}',
+ proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+ proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflict_reason,failover,sync_state}',
prosrc => 'pg_get_replication_slots' },
{ oid => '3786', descr => 'set up a logical replication slot',
proname => 'pg_create_logical_replication_slot', provolatile => 'v',
diff --git a/src/include/postmaster/bgworker.h b/src/include/postmaster/bgworker.h
index 22fc49ec27..7092fc72c6 100644
--- a/src/include/postmaster/bgworker.h
+++ b/src/include/postmaster/bgworker.h
@@ -79,6 +79,7 @@ typedef enum
BgWorkerStart_PostmasterStart,
BgWorkerStart_ConsistentState,
BgWorkerStart_RecoveryFinished,
+ BgWorkerStart_ConsistentState_HotStandby,
} BgWorkerStartTime;
#define BGW_DEFAULT_RESTART_INTERVAL 60
diff --git a/src/include/replication/logicalworker.h b/src/include/replication/logicalworker.h
index a18d79d1b2..bbe04226db 100644
--- a/src/include/replication/logicalworker.h
+++ b/src/include/replication/logicalworker.h
@@ -22,6 +22,7 @@ extern void TablesyncWorkerMain(Datum main_arg);
extern bool IsLogicalWorker(void);
extern bool IsLogicalParallelApplyWorker(void);
+extern bool IsLogicalSlotSyncWorker(void);
extern void HandleParallelApplyMessageInterrupt(void);
extern void HandleParallelApplyMessages(void);
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index 585ccbb504..b310b809c4 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -52,6 +52,22 @@ typedef enum ReplicationSlotInvalidationCause
RS_INVAL_WAL_LEVEL,
} ReplicationSlotInvalidationCause;
+/*
+ * The possible values for 'conflict_reason' returned in
+ * pg_get_replication_slots.
+ */
+#define SLOT_INVAL_WAL_REMOVED_TEXT "wal_removed"
+#define SLOT_INVAL_HORIZON_TEXT "rows_removed"
+#define SLOT_INVAL_WAL_LEVEL_TEXT "wal_level_insufficient"
+
+/* The possible values for 'sync_state' in ReplicationSlotPersistentData */
+#define SYNCSLOT_STATE_NONE 'n' /* None for user created slots */
+#define SYNCSLOT_STATE_INITIATED 'i' /* Sync initiated for the slot but
+ * not completed yet, waiting for
+ * the primary server to catch-up */
+#define SYNCSLOT_STATE_READY 'r' /* Initialization complete, ready
+ * to be synced further */
+
/*
* On-Disk data of a replication slot, preserved across restarts.
*/
@@ -112,6 +128,15 @@ typedef struct ReplicationSlotPersistentData
/* plugin name */
NameData plugin;
+ /*
+ * Synchronization state for a logical slot.
+ *
+ * The standby can have any value among the possible values of 'i','r' and
+ * 'n'. For primary, the default is 'n' for all slots but may also be 'r'
+ * if leftover from a promoted standby.
+ */
+ char sync_state;
+
/*
* Is this a failover slot (sync candidate for physical standbys)? Only
* relevant for logical slots on the primary server.
@@ -224,9 +249,11 @@ extern void ReplicationSlotsShmemInit(void);
/* management of individual slots */
extern void ReplicationSlotCreate(const char *name, bool db_specific,
ReplicationSlotPersistency persistency,
- bool two_phase, bool failover);
+ bool two_phase, bool failover,
+ char sync_state);
extern void ReplicationSlotPersist(void);
extern void ReplicationSlotDrop(const char *name, bool nowait);
+extern void ReplicationSlotDropAcquired(void);
extern void ReplicationSlotAlter(const char *name, bool failover);
extern void ReplicationSlotAcquire(const char *name, bool nowait);
diff --git a/src/include/replication/walreceiver.h b/src/include/replication/walreceiver.h
index f566a99ba1..9f78fd1e5a 100644
--- a/src/include/replication/walreceiver.h
+++ b/src/include/replication/walreceiver.h
@@ -279,6 +279,21 @@ typedef void (*walrcv_get_senderinfo_fn) (WalReceiverConn *conn,
typedef char *(*walrcv_identify_system_fn) (WalReceiverConn *conn,
TimeLineID *primary_tli);
+/*
+ * walrcv_get_dbinfo_for_failover_slots_fn
+ *
+ * Run LIST_DBID_FOR_FAILOVER_SLOTS on primary server to get the
+ * list of unique DBIDs for failover logical slots
+ */
+typedef List *(*walrcv_get_dbinfo_for_failover_slots_fn) (WalReceiverConn *conn);
+
+/*
+ * walrcv_get_dbname_from_conninfo_fn
+ *
+ * Returns the dbid from the primary_conninfo
+ */
+typedef char *(*walrcv_get_dbname_from_conninfo_fn) (const char *conninfo);
+
/*
* walrcv_server_version_fn
*
@@ -403,6 +418,7 @@ typedef struct WalReceiverFunctionsType
walrcv_get_conninfo_fn walrcv_get_conninfo;
walrcv_get_senderinfo_fn walrcv_get_senderinfo;
walrcv_identify_system_fn walrcv_identify_system;
+ walrcv_get_dbname_from_conninfo_fn walrcv_get_dbname_from_conninfo;
walrcv_server_version_fn walrcv_server_version;
walrcv_readtimelinehistoryfile_fn walrcv_readtimelinehistoryfile;
walrcv_startstreaming_fn walrcv_startstreaming;
@@ -428,6 +444,8 @@ extern PGDLLIMPORT WalReceiverFunctionsType *WalReceiverFunctions;
WalReceiverFunctions->walrcv_get_senderinfo(conn, sender_host, sender_port)
#define walrcv_identify_system(conn, primary_tli) \
WalReceiverFunctions->walrcv_identify_system(conn, primary_tli)
+#define walrcv_get_dbname_from_conninfo(conninfo) \
+ WalReceiverFunctions->walrcv_get_dbname_from_conninfo(conninfo)
#define walrcv_server_version(conn) \
WalReceiverFunctions->walrcv_server_version(conn)
#define walrcv_readtimelinehistoryfile(conn, tli, filename, content, size) \
diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h
index 4e1f6e7df9..e08e48debb 100644
--- a/src/include/replication/worker_internal.h
+++ b/src/include/replication/worker_internal.h
@@ -237,6 +237,11 @@ extern PGDLLIMPORT bool in_remote_transaction;
extern PGDLLIMPORT bool InitializingApplyWorker;
+/* Slot sync worker objects */
+extern PGDLLIMPORT char *PrimaryConnInfo;
+extern PGDLLIMPORT char *PrimarySlotName;
+extern PGDLLIMPORT bool enable_syncslot;
+
extern void logicalrep_worker_attach(int slot);
extern LogicalRepWorker *logicalrep_worker_find(Oid subid, Oid relid,
bool only_running);
@@ -326,6 +331,12 @@ extern void pa_decr_and_wait_stream_block(void);
extern void pa_xact_finish(ParallelApplyWorkerInfo *winfo,
XLogRecPtr remote_lsn);
+extern void ReplSlotSyncWorkerMain(Datum main_arg);
+extern void SlotSyncWorkerRegister(void);
+extern void ShutDownSlotSync(void);
+extern void slotsync_drop_initiated_slots(void);
+extern void SlotSyncWorkerShmemInit(void);
+
#define isParallelApplyWorker(worker) ((worker)->in_use && \
(worker)->type == WORKERTYPE_PARALLEL_APPLY)
#define isTablesyncWorker(worker) ((worker)->in_use && \
diff --git a/src/test/recovery/t/050_standby_failover_slots_sync.pl b/src/test/recovery/t/050_standby_failover_slots_sync.pl
index 796bf0a4af..c55a285ca3 100644
--- a/src/test/recovery/t/050_standby_failover_slots_sync.pl
+++ b/src/test/recovery/t/050_standby_failover_slots_sync.pl
@@ -97,6 +97,189 @@ ok( $publisher->poll_query_until(
"SELECT failover from pg_replication_slots WHERE slot_name = 'lsub1_slot';"),
'logical slot has failover true on the publisher');
-$subscriber1->safe_psql('postgres', "DROP SUBSCRIPTION regress_mysub1");
+##################################################
+# Test logical failover slots on the standby
+# Configure standby1 to replicate and synchronize logical slots configured
+# for failover on the primary
+#
+# failover slot lsub1_slot->| ----> subscriber1 (connected via logical replication)
+# primary ---> |
+# physical slot sb1_slot--->| ----> standby1 (connected via streaming replication)
+# | lsub1_slot(synced_slot)
+##################################################
+
+my $primary = $publisher;
+my $backup_name = 'backup';
+$primary->backup($backup_name);
+
+# Create a standby
+my $standby1 = PostgreSQL::Test::Cluster->new('standby1');
+$standby1->init_from_backup(
+ $primary, $backup_name,
+ has_streaming => 1,
+ has_restoring => 1);
+
+my $connstr_1 = $primary->connstr;
+$standby1->append_conf(
+ 'postgresql.conf', qq(
+enable_syncslot = true
+hot_standby_feedback = on
+primary_slot_name = 'sb1_slot'
+primary_conninfo = '$connstr_1 dbname=postgres'
+));
+
+$primary->psql('postgres',
+ q{SELECT pg_create_physical_replication_slot('sb1_slot');});
+
+my $standby1_conninfo = $standby1->connstr . ' dbname=postgres';
+
+# Wait for the standby to start sync
+my $offset = -s $standby1->logfile;
+$standby1->start;
+$standby1->wait_for_log(
+ qr/LOG: ( [A-Z0-9]+:)? waiting for remote slot \"lsub1_slot\"/,
+ $offset);
+
+# Advance lsn on the primary
+$primary->safe_psql('postgres',
+ "SELECT pg_log_standby_snapshot();
+ SELECT pg_log_standby_snapshot();
+ SELECT pg_log_standby_snapshot();");
+
+# Wait for the standby to finish sync
+$offset = -s $standby1->logfile;
+$standby1->wait_for_log(
+ qr/LOG: ( [A-Z0-9]+:)? wait over for remote slot \"lsub1_slot\"/,
+ $offset);
+
+# Confirm that logical failover slot is created on the standby and is sync
+# ready.
+is($standby1->safe_psql('postgres',
+ q{SELECT failover, sync_state FROM pg_replication_slots WHERE slot_name = 'lsub1_slot';}),
+ "t|ready",
+ 'logical slot has failover as true and sync_state as ready on standby');
+
+##################################################
+# Test to confirm that restart_lsn and confirmed_flush_lsn of the logical slot
+# on the primary is synced to the standby
+##################################################
+
+# Insert data on the primary
+$primary->safe_psql(
+ 'postgres', qq[
+ TRUNCATE TABLE tab_int;
+ INSERT INTO tab_int SELECT generate_series(1, 10);
+]);
+
+$primary->wait_for_catchup('regress_mysub1');
+
+# Do not allow any further advancement of the restart_lsn and
+# confirmed_flush_lsn for the lsub1_slot.
+$subscriber1->safe_psql('postgres', "ALTER SUBSCRIPTION regress_mysub1 DISABLE");
+
+# Wait for the replication slot to become inactive on the publisher
+$primary->poll_query_until(
+ 'postgres',
+ "SELECT COUNT(*) FROM pg_catalog.pg_replication_slots WHERE slot_name = 'lsub1_slot' AND active='f'",
+ 1);
+
+# Get the restart_lsn for the logical slot lsub1_slot on the primary
+my $primary_restart_lsn = $primary->safe_psql('postgres',
+ "SELECT restart_lsn from pg_replication_slots WHERE slot_name = 'lsub1_slot';");
+
+# Get the confirmed_flush_lsn for the logical slot lsub1_slot on the primary
+my $primary_flush_lsn = $primary->safe_psql('postgres',
+ "SELECT confirmed_flush_lsn from pg_replication_slots WHERE slot_name = 'lsub1_slot';");
+
+# Confirm that restart_lsn and of confirmed_flush_lsn lsub1_slot slot are synced
+# to the standby
+ok( $standby1->poll_query_until(
+ 'postgres',
+ "SELECT '$primary_restart_lsn' = restart_lsn AND '$primary_flush_lsn' = confirmed_flush_lsn from pg_replication_slots WHERE slot_name = 'lsub1_slot';"),
+ 'restart_lsn and confirmed_flush_lsn of slot lsub1_slot synced to standby');
+
+##################################################
+# Test that a synchronized slot can not be decoded, altered or dropped by the user
+##################################################
+
+# Disable hot_standby_feedback temporarily to stop slot sync worker otherwise
+# the concerned testing scenarios here may be interrupted by different error:
+# 'ERROR: replication slot is active for PID ..'
+
+$standby1->safe_psql('postgres', 'ALTER SYSTEM SET hot_standby_feedback = off;');
+$standby1->restart;
+
+# Attempting to perform logical decoding on a synced slot should result in an error
+my ($result, $stdout, $stderr) = $standby1->psql('postgres',
+ "select * from pg_logical_slot_get_changes('lsub1_slot',NULL,NULL);");
+ok($stderr =~ /ERROR: cannot use replication slot "lsub1_slot" for logical decoding/,
+ "logical decoding is not allowed on synced slot");
+
+# Attempting to alter a synced slot should result in an error
+($result, $stdout, $stderr) = $standby1->psql(
+ 'postgres',
+ qq[ALTER_REPLICATION_SLOT lsub1_slot (failover);],
+ replication => 'database');
+ok($stderr =~ /ERROR: cannot alter replication slot "lsub1_slot"/,
+ "synced slot on standby cannot be altered");
+
+# Attempting to drop a synced slot should result in an error
+($result, $stdout, $stderr) = $standby1->psql('postgres',
+ "SELECT pg_drop_replication_slot('lsub1_slot');");
+ok($stderr =~ /ERROR: cannot drop replication slot "lsub1_slot"/,
+ "synced slot on standby cannot be dropped");
+
+# Enable hot_standby_feedback and restart standby
+$standby1->safe_psql('postgres', 'ALTER SYSTEM SET hot_standby_feedback = on;');
+$standby1->restart;
+
+##################################################
+# Create another slot which stays in sync_state as 'initiated'
+# because it's a manually created slot and its lsn is not advanced.
+##################################################
+
+# Create a logical slot with failover = true
+$primary->psql('postgres',
+ q{SELECT pg_create_logical_replication_slot('logical_slot','pgoutput', false, true, true);});
+
+# Wait for the standby to start sync
+$offset = -s $standby1->logfile;
+$standby1->wait_for_log(
+ qr/LOG: ( [A-Z0-9]+:)? waiting for remote slot \"logical_slot\"/,
+ $offset);
+
+# Confirm that the logical slot is created on the standby and is in sync initiated state
+ is($standby1->safe_psql('postgres',
+ q{SELECT failover, sync_state FROM pg_replication_slots WHERE slot_name = 'logical_slot';}),
+ "t|initiated",
+ 'logical slot has failover as true and sync_state as initiated on standby');
+
+##################################################
+# Promote the standby1 to primary. Confirm that:
+# a) the 'ready' slot 'lsub1_slot' is retained on the new primary
+# b) the 'initiated' slot 'logical_slot' is dropped on promotion
+# c) logical replication for regress_mysub1 is resumed successfully after failover
+##################################################
+$standby1->promote;
+
+# Update subscription with the new primary's connection info
+$subscriber1->safe_psql('postgres',
+ "ALTER SUBSCRIPTION regress_mysub1 CONNECTION '$standby1_conninfo';
+ ALTER SUBSCRIPTION regress_mysub1 ENABLE; ");
+
+is($standby1->safe_psql('postgres',
+ q{SELECT slot_name FROM pg_replication_slots WHERE slot_name in ('logical_slot','lsub1_slot');}),
+ 'lsub1_slot',
+ 'synced slot retained on the new primary');
+
+# Insert data on the new primary
+$standby1->safe_psql('postgres',
+ "INSERT INTO tab_int SELECT generate_series(11, 20);");
+$standby1->wait_for_catchup('regress_mysub1');
+
+# Confirm that data in tab_int replicated on subscriber
+is( $subscriber1->safe_psql('postgres', q{SELECT count(*) FROM tab_int;}),
+ "20",
+ 'data replicated from the new primary');
done_testing();
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index acc2339b49..f5ccbf9ccb 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1474,8 +1474,9 @@ pg_replication_slots| SELECT l.slot_name,
l.safe_wal_size,
l.two_phase,
l.conflict_reason,
- l.failover
- FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflict_reason, failover)
+ l.failover,
+ l.sync_state
+ FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflict_reason, failover, sync_state)
LEFT JOIN pg_database d ON ((l.datoid = d.oid)));
pg_roles| SELECT pg_authid.rolname,
pg_authid.rolsuper,
diff --git a/src/test/regress/expected/sysviews.out b/src/test/regress/expected/sysviews.out
index 271313ebf8..aac83755de 100644
--- a/src/test/regress/expected/sysviews.out
+++ b/src/test/regress/expected/sysviews.out
@@ -132,8 +132,9 @@ select name, setting from pg_settings where name like 'enable%';
enable_self_join_removal | on
enable_seqscan | on
enable_sort | on
+ enable_syncslot | off
enable_tidscan | on
-(22 rows)
+(23 rows)
-- There are always wait event descriptions for various types.
select type, count(*) > 0 as ok FROM pg_wait_events
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9b67986914..b83f2143cd 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2321,6 +2321,7 @@ RelocationBufferInfo
RelptrFreePageBtree
RelptrFreePageManager
RelptrFreePageSpanLeader
+RemoteSlot
RenameStmt
ReopenPtrType
ReorderBuffer
@@ -2581,6 +2582,7 @@ SlabBlock
SlabContext
SlabSlot
SlotNumber
+SlotSyncWorkerCtx
SlruCtl
SlruCtlData
SlruErrorCause
--
2.34.1
view thread (28+ messages) latest in thread
reply
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: [email protected]
Cc: [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
Subject: Re: Synchronizing slots from primary to standby
In-Reply-To: <CAJpy0uDWgSBUsTav1Eeo7E7i38GjXr_o0WdWamm3jGdctcoC4A@mail.gmail.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox