ipvs: reduce sync rate with time thresholds

	Add two new sysctl vars to control the sync rate with the
main idea to reduce the rate for connection templates because
currently it depends on the packet rate for controlled connections.
This mechanism should be useful also for normal connections
with high traffic.

sync_refresh_period: in seconds, difference in reported connection
	timer that triggers new sync message. It can be used to
	avoid sync messages for the specified period (or half of
	the connection timeout if it is lower) if connection state
	is not changed from last sync.

sync_retries: integer, 0..3, defines sync retries with period of
	sync_refresh_period/8. Useful to protect against loss of
	sync messages.

	Allow sysctl_sync_threshold to be used with
sysctl_sync_period=0, so that only single sync message is sent
if sync_refresh_period is also 0.

	Add new field "sync_endtime" in connection structure to
hold the reported time when connection expires. The 2 lowest
bits will represent the retry count.

	As the sysctl_sync_period now can be 0 use ACCESS_ONCE to
avoid division by zero.

	Special thanks to Aleksey Chudov for being patient with me,
for his extensive reports and helping in all tests.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

1 files changed, 28 insertions, 2 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 30e43c8c0283..d3a4b934d521 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -504,6 +504,7 @@ struct ip_vs_conn {
 						 * state transition triggerd
 						 * synchronization
 						 */
+	unsigned long		sync_endtime;	/* jiffies + sent_retries */
 
 	/* Control members */
 	struct ip_vs_conn       *control;       /* Master control connection */
@@ -875,6 +876,8 @@ struct netns_ipvs {
 	int			sysctl_expire_nodest_conn;
 	int			sysctl_expire_quiescent_template;
 	int			sysctl_sync_threshold[2];
+	unsigned int		sysctl_sync_refresh_period;
+	int			sysctl_sync_retries;
 	int			sysctl_nat_icmp_send;
 
 	/* ip_vs_lblc */
@@ -916,10 +919,13 @@ struct netns_ipvs {
 #define DEFAULT_SYNC_THRESHOLD	3
 #define DEFAULT_SYNC_PERIOD	50
 #define DEFAULT_SYNC_VER	1
+#define DEFAULT_SYNC_REFRESH_PERIOD	(0U * HZ)
+#define DEFAULT_SYNC_RETRIES		0
 #define IPVS_SYNC_WAKEUP_RATE	8
 #define IPVS_SYNC_QLEN_MAX	(IPVS_SYNC_WAKEUP_RATE * 4)
 #define IPVS_SYNC_SEND_DELAY	(HZ / 50)
 #define IPVS_SYNC_CHECK_PERIOD	HZ
+#define IPVS_SYNC_FLUSH_TIME	(HZ * 2)
 
 #ifdef CONFIG_SYSCTL
 
@@ -930,7 +936,17 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
 
 static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 {
-	return ipvs->sysctl_sync_threshold[1];
+	return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]);
+}
+
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+	return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period);
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_retries;
 }
 
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
@@ -960,6 +976,16 @@ static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 	return DEFAULT_SYNC_PERIOD;
 }
 
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_REFRESH_PERIOD;
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_RETRIES & 3;
+}
+
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
 {
 	return DEFAULT_SYNC_VER;
@@ -1248,7 +1274,7 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
 			     __u8 syncid);
 extern int stop_sync_thread(struct net *net, int state);
-extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
 
 
 /*