diff options
| author | Eric Dumazet <edumazet@google.com> | 2013-08-28 18:10:43 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2013-08-30 17:48:04 -0400 |
| commit | 702821f4ea6f68db18aa1de7d8ed62c6ba586a64 (patch) | |
| tree | a0e3a4ba9577812f220224d7e6380146c193dc2e /net | |
| parent | 25ad6117e73656071b38fd19fa67ae325471c758 (diff) | |
net: revert 8728c544a9c ("net: dev_pick_tx() fix")
commit 8728c544a9cbdc ("net: dev_pick_tx() fix") and commit
b6fe83e9525a ("bonding: refine IFF_XMIT_DST_RELEASE capability")
are quite incompatible : Queue selection is disabled because skb
dst was dropped before entering bonding device.
This causes major performance regression, mainly because TCP packets
for a given flow can be sent to multiple queues.
This is particularly visible when using the new FQ packet scheduler
with MQ + FQ setup on the slaves.
We can safely revert the first commit now that 416186fbf8c5b
("net: Split core bits of netdev_pick_tx into __netdev_pick_tx")
properly caps the queue_index.
Reported-by: Xi Wang <xii@google.com>
Diagnosed-by: Xi Wang <xii@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Denys Fedorysychenko <nuclearcat@nuclearcat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
| -rw-r--r-- | net/core/flow_dissector.c | 11 |
1 files changed, 3 insertions, 8 deletions
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b84a1b155bc..d12e3a9a535 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -346,14 +346,9 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (new_index < 0) new_index = skb_tx_hash(dev, skb); - if (queue_index != new_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); - - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - - } + if (queue_index != new_index && sk && + rcu_access_pointer(sk->sk_dst_cache)) + sk_tx_queue_set(sk, queue_index); queue_index = new_index; } |