[IPVS]: Synchronize closing of Connections

This patch makes the master daemon to sync the connection when it is about
to close.  This makes the connections on the backup to close or timeout
according their state.  Before the sync was performed only if the
connection is in ESTABLISHED state which always made the connections to
timeout in the hard coded 3 minutes. However the Andy Gospodarek's patch
([IPVS]: use proper timeout instead of fixed value) effectively did nothing
more than increasing this to 15 minutes (Established state timeout).  So
this patch makes use of proper timeout since it syncs the connections on
status changes to FIN_WAIT (2min timeout) and CLOSE (10sec timeout).
However if the backup misses CLOSE hopefully it did not miss FIN_WAIT.
Otherwise we will just have to wait for the ESTABLISHED state timeout. As
it is without this patch.  This way the number of the hanging connections
on the backup is kept to minimum. And very few of them will be left to
timeout with a long timeout.

This is important if we want to make use of the fix for the real server
overcommit on master/backup fail-over.

Signed-off-by: Rumen G. Bogdanovski <rumen@voicecho.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 15 insertions, 7 deletions

diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index c6ed7654e83..20c884a5772 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -979,15 +979,23 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
 		ret = NF_ACCEPT;
 	}
 
-	/* increase its packet counter and check if it is needed
-	   to be synchronized */
+	/* Increase its packet counter and check if it is needed
+	 * to be synchronized
+	 *
+	 * Sync connection if it is about to close to
+	 * encorage the standby servers to update the connections timeout
+	 */
 	atomic_inc(&cp->in_pkts);
 	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
-	    (cp->protocol != IPPROTO_TCP ||
-	     cp->state == IP_VS_TCP_S_ESTABLISHED) &&
-	    (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
-	     == sysctl_ip_vs_sync_threshold[0]))
+	    (((cp->protocol != IPPROTO_TCP ||
+	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
+	      (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
+	       == sysctl_ip_vs_sync_threshold[0])) ||
+	     ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
+	      ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
+	       (cp->state == IP_VS_TCP_S_CLOSE)))))
 		ip_vs_sync_conn(cp);
+	cp->old_state = cp->state;
 
 	ip_vs_conn_put(cp);
 	return ret;
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index b1694d67abb..bd930efc18d 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -343,7 +343,6 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 			if (!dest) {
 				/* it is an unbound entry created by
 				 * synchronization */
-				cp->state = ntohs(s->state);
 				cp->flags = flags | IP_VS_CONN_F_HASHED;
 			} else
 				atomic_dec(&dest->refcnt);
@@ -358,6 +357,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 			p += SIMPLE_CONN_SIZE;
 
 		atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
+		cp->state = ntohs(s->state);
 		pp = ip_vs_proto_get(s->protocol);
 		cp->timeout = pp->timeout_table[cp->state];
 		ip_vs_conn_put(cp);