ipv4: percpu nh_rth_output cache
Input path is mostly run under RCU and doesnt touch dst refcnt
But output path on forwarding or UDP workloads hits
badly dst refcount, and we have lot of false sharing, for example
in ipv4_mtu() when reading rt->rt_pmtu
Using a percpu cache for nh_rth_output gives a nice performance
increase at a small cost.
24 udpflood test on my 24 cpu machine (dummy0 output device)
(each process sends 1.000.000 udp frames, 24 processes are started)
before : 5.24 s
after : 2.06 s
For reference, time on linux-3.5 : 6.60 s
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2bd1074..4f6276c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1206,11 +1206,15 @@
static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
{
- struct rtable *orig, *prev, **p = (struct rtable **)&nh->nh_rth_output;
+ struct rtable *orig, *prev, **p;
- if (rt_is_input_route(rt))
+ if (rt_is_input_route(rt)) {
p = (struct rtable **)&nh->nh_rth_input;
-
+ } else {
+ if (!nh->nh_pcpu_rth_output)
+ goto nocache;
+ p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+ }
orig = *p;
prev = cmpxchg(p, orig, rt);
@@ -1223,6 +1227,7 @@
* unsuccessful at storing this route into the cache
* we really need to set it.
*/
+nocache:
rt->dst.flags |= DST_NOCACHE;
}
}
@@ -1749,8 +1754,11 @@
fnhe = NULL;
if (fi) {
fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
- if (!fnhe) {
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_output);
+ if (!fnhe && FIB_RES_NH(*res).nh_pcpu_rth_output) {
+ struct rtable __rcu **prth;
+
+ prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+ rth = rcu_dereference(*prth);
if (rt_cache_valid(rth)) {
dst_hold(&rth->dst);
return rth;