From c7d4426a98a5f6654cd0b4b33d9dab2e77192c18 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 3 Oct 2010 22:17:54 -0700 Subject: [PATCH] net: introduce DST_NOCACHE flag While doing stress tests with IP route cache disabled, and multi queue devices, I noticed a very high contention on one rwlock used in neighbour code. When many cpus are trying to send frames (possibly using a high performance multiqueue device) to the same neighbour, they fight for the neigh->lock rwlock in order to call neigh_hh_init(), and fight on hh->hh_refcnt (a pair of atomic_inc/atomic_dec_and_test()) But we dont need to call neigh_hh_init() for dst that are used only once. It costs four atomic operations at least, on two contended cache lines, plus the high contention on neigh->lock rwlock. Introduce a new dst flag, DST_NOCACHE, that is set when dst was not inserted in route cache. With the stress test bench, sending 160000000 frames on one neighbour, results are : Before patch: real 2m28.406s user 0m11.781s sys 36m17.964s After patch: real 1m26.532s user 0m12.185s sys 20m3.903s Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 9 +++++---- net/core/neighbour.c | 4 +++- net/ipv4/route.c | 1 + 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/net/dst.h b/include/net/dst.h index aa53fbc34b2b..a217c838ec0d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -43,10 +43,11 @@ struct dst_entry { short error; short obsolete; int flags; -#define DST_HOST 1 -#define DST_NOXFRM 2 -#define DST_NOPOLICY 4 -#define DST_NOHASH 8 +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 unsigned long expires; unsigned short header_len; /* more space at head required */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 96b1a749abb4..b142a0d76072 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1210,7 +1210,9 @@ int neigh_resolve_output(struct sk_buff *skb) if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; - if (dev->header_ops->cache && !dst->hh) { + if (dev->header_ops->cache && + !dst->hh && + !(dst->flags & DST_NOCACHE)) { write_lock_bh(&neigh->lock); if (!dst->hh) neigh_hh_init(neigh, dst, dst->ops->protocol); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a61acea975f1..c3cb8bd23638 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1107,6 +1107,7 @@ restart: * on the route gc list. */ + rt->dst.flags |= DST_NOCACHE; if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { int err = arp_bind_neighbour(&rt->dst); if (err) { -- 2.30.2