Thanks for the answers. This is good enough. ;D
On Tue, Jun 25, 2013 at 2:25 PM, Ben Pfaff wrote:
> On Tue, Jun 25, 2013 at 02:14:49PM -0700, Alex Wang wrote:
> > But I still want to ask, what is the performance cost caused by using
> > vlan-splinter? Is that in that the using device driver can
On Tue, Jun 25, 2013 at 02:14:49PM -0700, Alex Wang wrote:
> But I still want to ask, what is the performance cost caused by using
> vlan-splinter? Is that in that the using device driver can be faster than
> matching datapath flow?
Looking up the splinter ports, on input and output, in an extra h
Sorry Ben for the bugging,
But I still want to ask, what is the performance cost caused by using
vlan-splinter? Is that in that the using device driver can be faster than
matching datapath flow?
Thanks a lot ;D
___
dev mailing list
dev@openvswitch.org
h
On Tue, Jun 25, 2013 at 01:33:33PM -0700, Alex Wang wrote:
> Thanks Ben,
>
> I noticed that my third comment was wrong by experiment. The following is
> just a resend of my previous email with the code review:
>
> "
>
> > 3. The packets with vlan header are missed in kernel and examined in
> > "
Thanks Ben,
I noticed that my third comment was wrong by experiment. The following is
just a resend of my previous email with the code review:
"
> 3. The packets with vlan header are missed in kernel and examined in
> "ofproto/ofproto-dpif.c". The "vsp_vlandev_to_realdev()" and
> "vsp_realdev_to
On Mon, Jun 24, 2013 at 10:16:15PM -0700, Alex Wang wrote:
> On Mon, Jun 24, 2013 at 6:13 PM, Alex Wang wrote:
>
> > Thanks for the answers,
> >
> > On Mon, Jun 24, 2013 at 5:03 PM, Ben Pfaff wrote:
> >
> >> On Mon, Jun 24, 2013 at 03:56:31PM -0700, Alex Wang wrote:
> >> > 1. What is usually the
>
> 3. The packets with vlan header are missed in kernel and examined in
> "ofproto/ofproto-dpif.c". The "vsp_vlandev_to_realdev()" and
> "vsp_realdev_to_vlandev()" are used to convert between "vlandev port" and
> "realdev port". And the performance cost is in that there is no datapath
> flow insta
On Mon, Jun 24, 2013 at 6:13 PM, Alex Wang wrote:
> Thanks for the answers,
>
> On Mon, Jun 24, 2013 at 5:03 PM, Ben Pfaff wrote:
>
>> On Mon, Jun 24, 2013 at 03:56:31PM -0700, Alex Wang wrote:
>> > 1. What is usually the bug in the buggy driver? How can using
>> vlan-splinter
>> > avoid that? I
Thanks for the answers,
On Mon, Jun 24, 2013 at 5:03 PM, Ben Pfaff wrote:
> On Mon, Jun 24, 2013 at 03:56:31PM -0700, Alex Wang wrote:
> > 1. What is usually the bug in the buggy driver? How can using
> vlan-splinter
> > avoid that? I'm a bit confused here, since the "vlandev.c" code still
> tal
On Mon, Jun 24, 2013 at 03:56:31PM -0700, Alex Wang wrote:
> 1. What is usually the bug in the buggy driver? How can using vlan-splinter
> avoid that? I'm a bit confused here, since the "vlandev.c" code still talks
> to linux device driver (e.g. when creating ADD_VLAN_CMD) via the "ioctl"
> call.
Thanks for the explanation,
Have few more questions below,
1. What is usually the bug in the buggy driver? How can using vlan-splinter
avoid that? I'm a bit confused here, since the "vlandev.c" code still talks
to linux device driver (e.g. when creating ADD_VLAN_CMD) via the "ioctl"
call.
2. If
On Mon, Jun 24, 2013 at 10:40:11AM -0700, Alex Wang wrote:
> I saw the AF_INET is used when creating the socket (to be used in
> "ioctl(sock, SIOCSIFVLAN, via)"). Seems to me that we cannot use netlink
> socket here, right? And, generally speaking, is that true that we can only
> use AF_INET, to ta
Hey Ben,
I'm learning vlan while reviewing this patch. Want to ask a question
unrelated to this patch but vlan.
I saw the AF_INET is used when creating the socket (to be used in
"ioctl(sock, SIOCSIFVLAN, via)"). Seems to me that we cannot use netlink
socket here, right? And, generally speaking,
CC: Ethan Jackson
Signed-off-by: Ben Pfaff
---
lib/dummy.c |3 +-
lib/dummy.h |3 +-
lib/vlandev.c | 346 +++
lib/vlandev.h |8 +-
tests/automake.mk |1 +
tests/ofproto-macros.at |9
14 matches
Mail list logo
