Scaling problem with a lot of AF_PACKET sockets on different interfaces

[Vitaly V. Bursov]

Hello,

I have a Linux router with a lot of interfaces (hundreds or
thousands of VLANs) and an application that creates AF_PACKET
socket per interface and bind()s sockets to interfaces.

Each socket has attached BPF filter too.

The problem is observed on linux-3.8.13, but as far I can see
from the source the latest version has alike behavior.

I noticed that box has strange performance problems with
most of the CPU time spent in __netif_receive_skb:
 86.15%  [k] __netif_receive_skb
  1.41%  [k] _raw_spin_lock
  1.09%  [k] fib_table_lookup
  0.99%  [k] local_bh_enable_ip

and this the assembly with the "hot spot":
       â       shr    $0x8,%r15w
       â       and    $0xf,%r15d
  0.00 â       shl    $0x4,%r15
       â       add    $0xffffffff8165ec80,%r15
       â       mov    (%r15),%rax
  0.09 â       mov    %rax,0x28(%rsp)
       â       mov    0x28(%rsp),%rbp
  0.01 â       sub    $0x28,%rbp
       â       jmp    5c7
  1.72 â5b0:   mov    0x28(%rbp),%rax
  0.05 â       mov    0x18(%rsp),%rbx
  0.00 â       mov    %rax,0x28(%rsp)
  0.03 â       mov    0x28(%rsp),%rbp
  5.67 â       sub    $0x28,%rbp
  1.71 â5c7:   lea    0x28(%rbp),%rax
  1.73 â       cmp    %r15,%rax
       â       je     640
  1.74 â       cmp    %r14w,0x0(%rbp)
       â       jne    5b0
 81.36 â       mov    0x8(%rbp),%rax
  2.74 â       cmp    %rax,%r8
       â       je     5eb
  1.37 â       cmp    0x20(%rbx),%rax
       â       je     5eb
  1.39 â       cmp    %r13,%rax
       â       jne    5b0
  0.04 â5eb:   test   %r12,%r12
  0.04 â       je     6f4
       â       mov    0xc0(%rbx),%eax
       â       mov    0xc8(%rbx),%rdx
       â       testb  $0x8,0x1(%rdx,%rax,1)
       â       jne    6d5

This corresponds to:

net/core/dev.c:
        type = skb->protocol;
        list_for_each_entry_rcu(ptype,
                        &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
                if (ptype->type == type &&
                    (ptype->dev == null_or_dev || ptype->dev == skb->dev ||
                     ptype->dev == orig_dev)) {
                        if (pt_prev)
                                ret = deliver_skb(skb, pt_prev, orig_dev);
                        pt_prev = ptype;
                }
        }

Which works perfectly OK until there are a lot of AF_PACKET sockets, since
the socket adds a protocol to ptype list:

# cat /proc/net/ptype
Type Device      Function
0800 eth2.1989 packet_rcv+0x0/0x400
0800 eth2.1987 packet_rcv+0x0/0x400
0800 eth2.1986 packet_rcv+0x0/0x400
0800 eth2.1990 packet_rcv+0x0/0x400
0800 eth2.1995 packet_rcv+0x0/0x400
0800 eth2.1997 packet_rcv+0x0/0x400
.......
0800 eth2.1004 packet_rcv+0x0/0x400
0800          ip_rcv+0x0/0x310
0011          llc_rcv+0x0/0x3a0
0004          llc_rcv+0x0/0x3a0
0806          arp_rcv+0x0/0x150

And this obviously results in a huge performance penalty.

ptype_all, by the looks, should be the same.

Probably one way to fix this it to perform interface name matching in
af_packet handler, but there could be other cases, other protocols.

Ideas are welcome :)

--
Thanks
Vitaly
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/