he separate process(es) solutions.
Giuseppe
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 56122 Pisa - Italy
Ph. : (+39) 050-2217.649 (direct) .599 (switch)
Fax : (+39) 050-2217.600
e-ma
scards packets from the fd of tap1. Now it is only the forwarding
thread that uses 99% CPU, while the main thread stays idle as expected. The
speedup in forwarding rate w.r.t. the unthreaded ovs-vswitchd is around 10x,
again.
Giuseppe
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria dell
e the corresponding
dpif_netdev_wait() callback would still be empty. Any comment would be
much appreciated.
Giuseppe
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 56122 Pisa - Italy
Ph. : (+39) 050-2217.649 (direct) .599
datapath. We are
trying to add Open Flow support in PlanetLab, and the Open vSwitch
userlevel datapath offers an easy solution for the integration (at
least, far more easier than the kernel datapath).
Giuseppe
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita
attention, for possible inclusion. As usual, any comment would be much
appreciated.
Regards,
Giuseppe
Il 27/08/2012 02:00, Ben Pfaff ha scritto:
On Fri, Aug 24, 2012 at 10:25:02AM +0200, Giuseppe Lettieri wrote:
Il 20/08/2012 20:48, Ed Maste ha scritto:
3. The datapath thread waits in poll() with
performance benefits might be
> related to how poll is used. Restructuring that seems like a much
> more desirable path but I never saw any real follow up. What was the
> reason for continuing to go down this path?
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
tinued
down this road.
I understand that our lack of time is no good reason to accept a patch. On the
other end, I tried to push it anyway since it solves a real problem for FreeBSD
people, maybe also PlanetLab users, and possibly others.
Giuseppe
Dr. Ing. Giuseppe Lettieri
Dipartimento di Inge
Hi everybody,
I am Giuseppe Lettieri from Pisa (Italy) and I am working on integrating
Open vSwitch in PlanetLab. We are currently focusing on the user level
(aka 'netdev') datapath, since this is much simpler to use in PlanetLab.
I have noticed that if I create a bridge with
.
Best regards,
Giuseppe
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 56122 Pisa - Italy
Ph. : (+39) 050-2217.649 (direct) .599 (switch)
Fax : (+39) 050-2217.600
e-mail: g.letti...@iet.unipi.it
>From 3325f9aa0d145
On 11/05/2012 18:52, Ben Pfaff wrote:
Will you give me a Signed-off-by: line for this, for example:
Signed-off-by: Giuseppe Lettieri
By doing this, you are agreeing to the Developer's Certificate of Origin
(see below for more details).
Ok, but I don't know how this wo
merate function pointer is set to NULL.
> Thus for the netdev-based
> datapath, the names sset is still empty after calling
> ofproto_enumerate_names. The ofproto_delete
> will not be called at all.
>
> Am I missing something?
>
>
> ___
with netlink. If you are interested, we would like to
also share the more substantial patches when we have finished testing them.
Best regards,
Giuseppe Lettieri
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 56122
Sorry, here is the patch that was to supposed to be attached to the
previous message.
Best regards,
Giuseppe Lettieri
Il 28/06/2012 11:10, Giuseppe Lettieri ha scritto:
> Hi,
>
> we are working on a port of Open vSwitch to FreeBSD. This patch is a
> first step toward that direct
ting on
this porting, we thought that we could benefit from developers' comments.
Best regards,
Giuseppe Lettieri
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 56122 Pisa - Italy
Ph. : (+39) 050-2217.649 (direct)
07/07/2012 03:29, Ben Pfaff ha scritto:
> On Fri, Jul 06, 2012 at 02:59:05PM +0200, Giuseppe Lettieri wrote:
>> the attached patch implements new netdev classes for "system" and "tap"
>> devices in FreeBSD, by using the libpcap library. With this patch (and
>
t work without this issue being
> fixed.
>
> There's a line of commented-out code in netdev_bsd_get_stats():
> //COVERAGE_INC(netdev_get_stats);
> Also in set_etheraddr():
> //COVERAGE_INC(netdev_set_hwaddr);
>
> Let me know what you think.
>
The VLOG thing is
ll rules, like
iptables -A INPUT -i eth_n -j DROP
iptables -A FORWARD -i eth_n -j DROP
for each eth_n which is connected to an ovs bridge.
Thoughts?
Giuseppe
--
Dr. Ing. Giuseppe Lettieri
Dipartimento di Ingegneria della Informazione
Universita' di Pisa
Largo Lucio Lazzarino 2, 5612
of tap1. In all cases,
ovs-vswitchd had called netdev_linux_listen() on both tap0 and tap1, and
therefore the branch in netdev_linux_send that uses the global AF_PACKET
socket was not taken.
Can you please point out a scenario that actually makes use of the
global socket? That would be very hel
18 matches
Mail list logo
