diff options
| author | Paolo Abeni <pabeni@redhat.com> | 2017-05-16 11:20:14 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2017-05-16 15:41:29 -0400 |
| commit | 2276f58ac5890e58d2b6a48b95493faff7347e3a (patch) | |
| tree | c77ce6fd0b942dfddb145e1ad6dbb2fb1942d849 /net/ipv6/udp.c | |
| parent | 65101aeca52241a05e66f23c96eb896c9412718d (diff) | |
udp: use a separate rx queue for packet reception
under udp flood the sk_receive_queue spinlock is heavily contended.
This patch try to reduce the contention on such lock adding a
second receive queue to the udp sockets; recvmsg() looks first
in such queue and, only if empty, tries to fetch the data from
sk_receive_queue. The latter is spliced into the newly added
queue every time the receive path has to acquire the
sk_receive_queue lock.
The accounting of forward allocated memory is still protected with
the sk_receive_queue lock, so udp_rmem_release() needs to acquire
both locks when the forward deficit is flushed.
On specific scenarios we can end up acquiring and releasing the
sk_receive_queue lock multiple times; that will be covered by
the next patch
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6/udp.c')
| -rw-r--r-- | net/ipv6/udp.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04862abfe4ec..f78fdf8c9f0f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -455,7 +455,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { if (is_udp4) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); |