Hello,
Please find the patch as an attachment.
Any comment is welcome.
Francois-Xavier Le Bail
___
tcpdump-workers mailing list
tcpdump-workers@lists.tcpdump.org
https://lists.sandelman.ca/mailman/listinfo/tcpdump-workers
Hello,
Please find the patch version 2 as an attachment.
Updated for more tests on lengths.
Any comment is welcome.
Francois-Xavier
- Original Message -
> From: François-Xavier Le Bail
> To: "tcpdump-workers@lists.tcpdump.org"
> Cc: "fx.leb...@yahoo.com"
> Sent: Wednesday, Novemb
Ani Sinha writes:
> cc'ing netdev.
>
>
> On Wed, Oct 31, 2012 at 2:01 PM, Michael Richardson wrote:
>>
>> Thanks for this email.
>>
>>> "Ani" == Ani Sinha writes:
>> Ani> remove "inline" from vlan_core.c functions
>> Ani> Signed-off-by: David S. Miller
>>
>> Ani> As a result of
On Sat, Nov 17, 2012 at 11:14 PM, Michael Richardson wrote:
>
> Thank you for this reply.
>
>> "Eric" == Eric W Biederman writes:
> Eric> I don't see any need to add any kernel code to allow checking
> Eric> if vlan tags are stripped. Vlan headers are stripped on all
> Eric> kern
Michael Richardson writes:
> Thank you for this reply.
>
>> "Eric" == Eric W Biederman writes:
> Eric> I don't see any need to add any kernel code to allow checking
> Eric> if vlan tags are stripped. Vlan headers are stripped on all
> Eric> kernel interfaces today. Vlan headers
Daniel Borkmann writes:
> Speaking of netsniff-ng where we don't reconstruct VLAN headers, users
> have reported that depending on the NIC/driver resp. ethtool setting,
> they can come in stripped or not (in the pf_packet's rx_ring buffer).
> However, I assume VLAN AUXDATA is always consistent (a
> hi,
> I just checked the two mechanism :
> (1) Using mmap to fetch packets from kernel to userspace
> (2) Using recvfrom() call to fetch packets
>
> I see top reports
> (1) 34% memory 20% cpu usage
> (2) 21% memory 7% cpu usage !
It is worth remembering that the cpu usage reported by top isn'
