ipvs: allow rescheduling of new connections when port reuse is detected

Currently, when TCP/SCTP port reusing happens, IPVS will find the old
entry and use it for the new one, behaving like a forced persistence.
But if you consider a cluster with a heavy load of small connections,
such reuse will happen often and may lead to a not optimal load
balancing and might prevent a new node from getting a fair load.

This patch introduces a new sysctl, conn_reuse_mode, that allows
controlling how to proceed when port reuse is detected. The default
value will allow rescheduling of new connections only if the old entry
was in TIME_WAIT state for TCP or CLOSED for SCTP.

Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

1 files changed, 11 insertions, 0 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a627fe690c19..20fd23398537 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -941,6 +941,7 @@ struct netns_ipvs {
         int                     sysctl_nat_icmp_send;
         int                     sysctl_pmtu_disc;
         int                     sysctl_backup_only;
+        int                     sysctl_conn_reuse_mode;
 
         /* ip_vs_lblc */
         int                     sysctl_lblc_expiration;
@@ -1059,6 +1060,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
                ipvs->sysctl_backup_only;
 }
 
+static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs)
+{
+        return ipvs->sysctl_conn_reuse_mode;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1126,6 +1132,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
         return 0;
 }
 
+static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs)
+{
+        return 1;
+}
+
 #endif
 
 /* IPVS core functions