ipvs: avoid overcommit on the standby, take II

Index: net-2.6/include/net/ip_vs.h
===================================================================
@@ -901,6 +901,10 @@ extern int ip_vs_use_count_inc(void);
 extern void ip_vs_use_count_dec(void);
 extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
+extern struct ip_vs_dest *
+ip_vs_find_dest(__be32 daddr, __be16 dport,
+		 __be32 vaddr, __be16 vport, __u16 protocol);
+extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
 /*

Index: net-2.6/net/ipv4/ipvs/ip_vs_conn.c
===================================================================
@@ -426,6 +426,25 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, s
 
 
 /*
+ * Check if there is a destination for the connection, if so
+ * bind the connection to the destination.
+ */
+struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
+{
+	struct ip_vs_dest *dest;
+
+	if ((cp) && (!cp->dest)) {
+		dest = ip_vs_find_dest(cp->daddr, cp->dport,
+				       cp->vaddr, cp->vport, cp->protocol);
+		ip_vs_bind_dest(cp, dest);
+		return dest;
+	} else
+		return NULL;
+}
+EXPORT_SYMBOL(ip_vs_try_bind_dest);
+
+
+/*
  *	Unbind a connection entry with its VS destination
  *	Called by the ip_vs_conn_expire function.
  */

Index: net-2.6/net/ipv4/ipvs/ip_vs_ctl.c
===================================================================
@@ -579,6 +579,34 @@ ip_vs_lookup_dest(struct ip_vs_service *
 	return NULL;
 }
 
+/*
+ * Find destination by {daddr,dport,vaddr,protocol}
+ * Cretaed to be used in ip_vs_process_message() in
+ * the backup synchronization daemon. It finds the
+ * destination to be bound to the received connection
+ * on the backup.
+ *
+ * ip_vs_lookup_real_service() looked promissing, but
+ * seems not working as expected.
+ */
+struct ip_vs_dest *ip_vs_find_dest(__be32 daddr, __be16 dport,
+				    __be32 vaddr, __be16 vport,
+				    __u16 protocol)
+{
+	struct ip_vs_dest *dest;
+	struct ip_vs_service *svc;
+
+	svc = ip_vs_service_get(0, protocol, vaddr, vport);
+	if (!svc)
+		return NULL;
+	dest = ip_vs_lookup_dest(svc, daddr, dport);
+	if (dest)
+		atomic_inc(&dest->refcnt);
+	ip_vs_service_put(svc);
+
+	return dest;
+}
+EXPORT_SYMBOL(ip_vs_find_dest);
 
 /*
  *  Lookup dest by {svc,addr,port} in the destination trash.

Index: net-2.6/net/ipv4/ipvs/ip_vs_sync.c
===================================================================
@@ -284,6 +284,7 @@ static void ip_vs_process_message(const 
 	struct ip_vs_sync_conn_options *opt;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_dest *dest;
 	char *p;
 	int i;
 

@@ -317,20 +318,35 @@ static void ip_vs_process_message(const 
 					       s->caddr, s->cport,
 					       s->vaddr, s->vport);
 		if (!cp) {
+			/*
+			 * Find the appropriate destination for the connection.
+			 * If it is not found the connection will remain unbound
+			 * but still handled.
+			 */
+			dest = ip_vs_find_dest(s->daddr, s->dport,
+					       s->vaddr, s->vport,
+					       s->protocol);
 			cp = ip_vs_conn_new(s->protocol,
 					    s->caddr, s->cport,
 					    s->vaddr, s->vport,
 					    s->daddr, s->dport,
-					    flags, NULL);
+					    flags, dest);
+			if (dest)
+				atomic_dec(&dest->refcnt);
 			if (!cp) {
 				IP_VS_ERR("ip_vs_conn_new failed\n");
 				return;
 			}
 			cp->state = ntohs(s->state);
 		} else if (!cp->dest) {
-			/* it is an entry created by the synchronization */
-			cp->state = ntohs(s->state);
-			cp->flags = flags | IP_VS_CONN_F_HASHED;
+			dest = ip_vs_try_bind_dest(cp);
+			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);
 		}	/* Note that we don't touch its state and flags
 			   if it is a normal entry. */
 

Index: net-2.6/include/net/ip_vs.h
===================================================================
@@ -520,6 +520,10 @@ struct ip_vs_conn {
 	spinlock_t              lock;           /* lock for state transition */
 	volatile __u16          flags;          /* status flags */
 	volatile __u16          state;          /* state info */
+	volatile __u16          old_state;      /* old state, to be used for
+						 * state transition triggerd
+						 * synchronization
+						 */
 
 	/* Control members */
 	struct ip_vs_conn       *control;       /* Master control connection */

Index: net-2.6/net/ipv4/ipvs/ip_vs_core.c
===================================================================
@@ -979,15 +979,23 @@ ip_vs_in(unsigned int hooknum, struct sk
 		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;

Index: net-2.6/net/ipv4/ipvs/ip_vs_sync.c
===================================================================
@@ -332,7 +332,7 @@ static void ip_vs_process_message(const 
 					    s->daddr, s->dport,
 					    flags, dest);
 			if (dest)
-				atomic_dec(&dest->refcnt);
+				ip_vs_dest_get(dest);
 			if (!cp) {
 				IP_VS_ERR("ip_vs_conn_new failed\n");
 				return;

@@ -343,10 +343,9 @@ static void ip_vs_process_message(const 
 			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);
+				ip_vs_dest_put(dest);
 		}	/* Note that we don't touch its state and flags
 			   if it is a normal entry. */
 

@@ -358,6 +357,7 @@ static void ip_vs_process_message(const 
 			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);