dummynet dropping too many packets

[rihad]

Oleg Bulyzhin wrote:
> On Wed, Oct 07, 2009 at 03:52:56PM +0500, rihad wrote:
> 
>> You probably have some special sources of documentation ;-) According to 
>> man ipfw, both "netgraph/ngtee" and "pipe" decide the fate of the packet 
>> unless one_pass=0. Or do you mean sprinkling smart skiptos here and 
>> there? ;-)
> 
> you can
> 1) use ng_ether & ng_netflow. (so no need in 'ngtee' rule).
> 2) use 'tee' rule with ng_ksocket & ng_netflow
> 
Thanks, I'll see into that if fast-forwarding doesn't help.

>>> Could you show your 'ipfw show' output? (hide ip addresses if you wish but
>>> keep counters please).
>>>
> 
>> Here it is, in its whole glory:
>>
>> 00100   10434423   1484891105 allow ip from any to any via lo0
>> 00200          2           14 deny ip from any to 127.0.0.0/8
>> 00300          1            4 deny ip from 127.0.0.0/8 to any
>> 01000 3300039938 327603104711 allow ip from any to any in
>> 01010   26214900    421138433 allow ip from me to any out
>> 01020    5453857     46806278 allow icmp from any to any out
>> 01030 3268289053 327224694165 ngtee 1 ip from any to any out
>> 01040   18681181   1089636054 skipto 1100 ip from table(127) to any out 
>> recv bce0 xmit bce1
>> 01060  777488848  76743392754 pipe tablearg ip from any to table(0) out 
>> recv bce0 xmit bce1
>> 01070  776831109  76682499457 allow ip from any to table(0) out recv 
>> bce0 xmit bce1
>> 01100   13102697    808411842 pipe tablearg ip from any to table(2) out
>> 65535  662648946  66711487830 allow ip from any to any
> 
> I guess this one would be better(faster):
> 
> 00050 allow ip from any to any in
> 00100 allow ip from any to any via lo0
> 01010 allow ip from me to any
> 01020 allow icmp from any to any
> 01030 ngtee 1 ip from any to any
> 01035 skipto 1040 ip from any to any recv bce0 xmit bce1
> 01036 allow ip from any to any
> 01040 skipto 1100 ip from table(127) to any
> 01060 pipe tablearg ip from any to table(0)
> 01070 allow ip from any to any
> 01100 pipe tablearg ip from any to table(2)
> 65535 allow ip from any to any
> 
Phew, were "out" that bad? I left them in as commentary.
And the localhost anti-spoof check isn't such a bad security ring to get 
rid of in the name of performance ;-)
Ok, got you, I'll take a note of it, thanks.

> P.S. have you tried net.inet.ip.fastforwarding=1?
> 
man 4 inet:
      IPCTL_FASTFORWARDING  (ip.fastforwarding) Boolean: enable/disable 
the use
                            of fast IP forwarding code.  Defaults to 
off.  When
                            fast IP forwarding is enabled, IP packets 
are for-
                            warded directly to the appropriate network 
inter-
                            face with direct processing to completion, which
                            greatly improves the throughput.  All 
packets for
                            local IP addresses, non-unicast, or with IP 
options
                            are handled by the normal IP input 
processing path.
                            All features of the normal (slow) IP forwarding
                            path are supported including firewall (through
                            pfil(9) hooks) checking, except ipsec(4) tunnel
                            brokering.  The IP fastforwarding path does not
                            generate ICMP redirect or source quench 
messages.

I'm afraid a bit that it will lock up the live remote system. Is it a 
drop in replacement given my ipfw rules? Why isn't it enabled by default?