diff options
| author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-10-03 22:17:54 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2010-10-03 22:17:54 -0700 |
| commit | c7d4426a98a5f6654cd0b4b33d9dab2e77192c18 (patch) | |
| tree | 0db2524e6f3f742861765dd6aa696a9271767056 /net | |
| parent | 9a7241c21b06c3a3f8ebcf3e347bd68556369da7 (diff) | |
| download | kernel_samsung_tuna-c7d4426a98a5f6654cd0b4b33d9dab2e77192c18.zip kernel_samsung_tuna-c7d4426a98a5f6654cd0b4b33d9dab2e77192c18.tar.gz kernel_samsung_tuna-c7d4426a98a5f6654cd0b4b33d9dab2e77192c18.tar.bz2 | |
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 <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
| -rw-r--r-- | net/core/neighbour.c | 4 | ||||
| -rw-r--r-- | net/ipv4/route.c | 1 |
2 files changed, 4 insertions, 1 deletions
diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 96b1a749a..b142a0d 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 a61acea..c3cb8bd 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) { |