ipvs: improved SH fallback strategy

Improve the SH fallback realserver selection strategy.

With sh and sh-fallback, if a realserver is down, this attempts to
distribute the traffic that would have gone to that server evenly
among the remaining servers.

Signed-off-by: Alexander Frolkin <avf@eldamar.org.uk>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

1 files changed, 29 insertions, 10 deletions

diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 3588faebe529..cc65b2f42cd4 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -115,27 +115,46 @@ ip_vs_sh_get(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
 }
 
 
-/* As ip_vs_sh_get, but with fallback if selected server is unavailable */
+/* As ip_vs_sh_get, but with fallback if selected server is unavailable
+ *
+ * The fallback strategy loops around the table starting from a "random"
+ * point (in fact, it is chosen to be the original hash value to make the
+ * algorithm deterministic) to find a new server.
+ */
 static inline struct ip_vs_dest *
 ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
                       const union nf_inet_addr *addr, __be16 port)
 {
-        unsigned int offset;
-        unsigned int hash;
+        unsigned int offset, roffset;
+        unsigned int hash, ihash;
         struct ip_vs_dest *dest;
 
+        /* first try the dest it's supposed to go to */
+        ihash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
+        dest = rcu_dereference(s->buckets[ihash].dest);
+        if (!dest)
+                return NULL;
+        if (!is_unavailable(dest))
+                return dest;
+
+        IP_VS_DBG_BUF(6, "SH: selected unavailable server %s:%d, reselecting",
+                      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+
+        /* if the original dest is unavailable, loop around the table
+         * starting from ihash to find a new dest
+         */
         for (offset = 0; offset < IP_VS_SH_TAB_SIZE; offset++) {
-                hash = ip_vs_sh_hashkey(svc->af, addr, port, offset);
+                roffset = (offset + ihash) % IP_VS_SH_TAB_SIZE;
+                hash = ip_vs_sh_hashkey(svc->af, addr, port, roffset);
                 dest = rcu_dereference(s->buckets[hash].dest);
                 if (!dest)
                         break;
-                if (is_unavailable(dest))
-                        IP_VS_DBG_BUF(6, "SH: selected unavailable server "
-                                      "%s:%d (offset %d)",
-                                      IP_VS_DBG_ADDR(svc->af, &dest->addr),
-                                      ntohs(dest->port), offset);
-                else
+                if (!is_unavailable(dest))
                         return dest;
+                IP_VS_DBG_BUF(6, "SH: selected unavailable "
+                              "server %s:%d (offset %d), reselecting",
+                              IP_VS_DBG_ADDR(svc->af, &dest->addr),
+                              ntohs(dest->port), roffset);
         }
 
         return NULL;