From: Martin Schwenke <mschwenke@ddn.com>
Date: Sun, 18 May 2025 23:06:38 +0000 (+1000)
Subject: ctdb-daemon: Add configuration option shutdown extra timeout
X-Git-Tag: samba-4.21.6~4
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3a16697b9b23f962869eacbff128d68833d537d9;p=thirdparty%2Fsamba.git

ctdb-daemon: Add configuration option shutdown extra timeout

See documentation change for details.

BUG: https://bugzilla.samba.org/show_bug.cgi?id=15858

Signed-off-by: Martin Schwenke <mschwenke@ddn.com>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
(cherry picked from commit 3a770c8d46934870f42059640b0aaa0c76a3f4fb)
---

diff --git a/ctdb/conf/ctdb_config.c b/ctdb/conf/ctdb_config.c
index 03649836e3f..27623a8972a 100644
--- a/ctdb/conf/ctdb_config.c
+++ b/ctdb/conf/ctdb_config.c
@@ -106,6 +106,10 @@ static void setup_config_pointers(struct conf_context *conf)
 				    FAILOVER_CONF_SECTION,
 				    FAILOVER_CONF_DISABLED,
 				    &ctdb_config.failover_disabled);
+	conf_assign_integer_pointer(conf,
+				    FAILOVER_CONF_SECTION,
+				    FAILOVER_CONF_SHUTDOWN_EXTRA_TIMEOUT,
+				    &ctdb_config.shutdown_extra_timeout);
 	conf_assign_integer_pointer(conf,
 				    FAILOVER_CONF_SECTION,
 				    FAILOVER_CONF_SHUTDOWN_FAILOVER_TIMEOUT,
diff --git a/ctdb/conf/ctdb_config.h b/ctdb/conf/ctdb_config.h
index b3ae5a43580..656a99e36bc 100644
--- a/ctdb/conf/ctdb_config.h
+++ b/ctdb/conf/ctdb_config.h
@@ -43,6 +43,7 @@ struct ctdb_config {
 
 	/* Failover */
 	bool failover_disabled;
+	int shutdown_extra_timeout;
 	int shutdown_failover_timeout;
 
 	/* Legacy */
diff --git a/ctdb/conf/failover_conf.c b/ctdb/conf/failover_conf.c
index 01b0b617827..424021b7a22 100644
--- a/ctdb/conf/failover_conf.c
+++ b/ctdb/conf/failover_conf.c
@@ -51,6 +51,12 @@ void failover_conf_init(struct conf_context *conf)
 			    false,
 			    check_static_boolean_change);
 
+	conf_define_integer(conf,
+			    FAILOVER_CONF_SECTION,
+			    FAILOVER_CONF_SHUTDOWN_EXTRA_TIMEOUT,
+			    0,
+			    NULL);
+
 	conf_define_integer(conf,
 			    FAILOVER_CONF_SECTION,
 			    FAILOVER_CONF_SHUTDOWN_FAILOVER_TIMEOUT,
diff --git a/ctdb/conf/failover_conf.h b/ctdb/conf/failover_conf.h
index 34ab9c193b3..08f5fb8939c 100644
--- a/ctdb/conf/failover_conf.h
+++ b/ctdb/conf/failover_conf.h
@@ -25,6 +25,7 @@
 #define FAILOVER_CONF_SECTION "failover"
 
 #define FAILOVER_CONF_DISABLED "disabled"
+#define FAILOVER_CONF_SHUTDOWN_EXTRA_TIMEOUT "shutdown extra timeout"
 #define FAILOVER_CONF_SHUTDOWN_FAILOVER_TIMEOUT "shutdown failover timeout"
 
 
diff --git a/ctdb/doc/ctdb.conf.5.xml b/ctdb/doc/ctdb.conf.5.xml
index d7d2f5395eb..5b2de2b7a07 100644
--- a/ctdb/doc/ctdb.conf.5.xml
+++ b/ctdb/doc/ctdb.conf.5.xml
@@ -454,6 +454,37 @@
 	</listitem>
       </varlistentry>
 
+      <varlistentry>
+	<term>shutdown extra timeout = <parameter>TIMEOUT</parameter></term>
+	<listitem>
+	  <para>
+	    CTDB will wait for TIMEOUT seconds after failover
+	    completes during shutdown.  This can provide extra time
+	    for SMB durable handles to be reclaimed.  If set to 0 then
+	    no extra timeout occurs.
+	  </para>
+	  <para>
+	    This timeout only occurs if both of the following
+	    conditions are true:
+	  </para>
+	  <itemizedlist>
+	    <listitem>
+	      <para>
+		shutdown failover timeout (below) is not 0
+	      </para>
+	    </listitem>
+	    <listitem>
+	      <para>
+		Failover during shutdown completes and does not time out
+	      </para>
+	    </listitem>
+	  </itemizedlist>
+	  <para>
+	    Default: <literal>0</literal>
+	  </para>
+	</listitem>
+      </varlistentry>
+
       <varlistentry>
 	<term>shutdown failover timeout = <parameter>TIMEOUT</parameter></term>
 	<listitem>
@@ -461,7 +492,8 @@
 	    CTDB will wait for TIMEOUT seconds for failover to
 	    complete during shutdown.  This allows NFS servers on
 	    other nodes to go into grace during graceful shutdown of a
-	    node.
+	    node.  Failover during shutdown also helps with SMB
+	    durable handle reclaim.
 	  </para>
 	  <para>
 	    Set this to 0 to disable explicit failover on shutdown.
diff --git a/ctdb/server/ctdb_daemon.c b/ctdb/server/ctdb_daemon.c
index 3d07e6e8c3d..1fd646c3758 100644
--- a/ctdb/server/ctdb_daemon.c
+++ b/ctdb/server/ctdb_daemon.c
@@ -2416,6 +2416,29 @@ done:
 	srvid_deregister(ctdb->srv, CTDB_SRVID_TAKEOVER_RUN, &state);
 	srvid_deregister(ctdb->srv, CTDB_SRVID_LEADER, &state);
 	TALLOC_FREE(state.te);
+
+	if (!state.takeover_done || ctdb_config.shutdown_extra_timeout <= 0) {
+		return;
+	}
+
+	state.timed_out = false;
+	state.te = tevent_add_timer(
+		ctdb->ev,
+		ctdb->srv,
+		timeval_current_ofs(ctdb_config.shutdown_extra_timeout, 0),
+		shutdown_timeout_handler,
+		&state);
+	if (state.te == NULL) {
+		DBG_WARNING("Failed to set extra timeout\n");
+		return;
+	}
+
+	DBG_NOTICE("Waiting %ds for shutdown extra timeout\n",
+		   ctdb_config.shutdown_extra_timeout);
+	while (!state.timed_out) {
+		tevent_loop_once(ctdb->ev);
+	}
+	DBG_INFO("shutdown extra timeout complete\n");
 }
 
 void ctdb_shutdown_sequence(struct ctdb_context *ctdb, int exit_code)
diff --git a/ctdb/tests/UNIT/cunit/config_test_001.sh b/ctdb/tests/UNIT/cunit/config_test_001.sh
index 1cf49a820de..b4d784c65ae 100755
--- a/ctdb/tests/UNIT/cunit/config_test_001.sh
+++ b/ctdb/tests/UNIT/cunit/config_test_001.sh
@@ -48,6 +48,7 @@ ok <<EOF
 	# debug script = 
 [failover]
 	# disabled = false
+	# shutdown extra timeout = 0
 	# shutdown failover timeout = 10
 [legacy]
 	# realtime scheduling = true