net dst: use a percpu_counter to track entries

struct dst_ops tracks number of allocated dst in an atomic_t field,
subject to high cache line contention in stress workload.

Switch to a percpu_counter, to reduce number of time we need to dirty a
central location. Place it on a separate cache line to avoid dirtying
read only fields.

Stress test :

(Sending 160.000.000 UDP frames,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_TRIE, SLUB/NUMA)

Before:

real    0m51.179s
user    0m15.329s
sys     10m15.942s

After:

real	0m45.570s
user	0m15.525s
sys	9m56.669s

With a small reordering of struct neighbour fields, subject of a
following patch, (to separate refcnt from other read mostly fields)

real	0m41.841s
user	0m15.261s
sys	8m45.949s

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 2 insertions, 1 deletions

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 6585ea6d1182..df0f3e54ff8a 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -132,7 +132,6 @@ static struct dst_ops dn_dst_ops = {
         .negative_advice =      dn_dst_negative_advice,
         .link_failure =         dn_dst_link_failure,
         .update_pmtu =          dn_dst_update_pmtu,
-        .entries =              ATOMIC_INIT(0),
 };
 
 static __inline__ unsigned dn_hash(__le16 src, __le16 dst)
@@ -1758,6 +1757,7 @@ void __init dn_route_init(void)
         dn_dst_ops.kmem_cachep =
                 kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0,
                                   SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+        dst_entries_init(&dn_dst_ops);
         setup_timer(&dn_route_timer, dn_dst_check_expire, 0);
         dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ;
         add_timer(&dn_route_timer);
@@ -1816,5 +1816,6 @@ void __exit dn_route_cleanup(void)
         dn_run_flush(0);
 
         proc_net_remove(&init_net, "decnet_cache");
+        dst_entries_destroy(&dn_dst_ops);
 }