> On Wed, Jun 25, 2014 at 11:07:31AM +0900, YAMAMOTO Takashi wrote:
>> Signed-off-by: YAMAMOTO Takashi
>> ---
>> FAQ | 6 ++
>> 1 file changed, 6 insertions(+)
>>
>> diff --git a/FAQ b/FAQ
>> index 79d905d..c2520fc 100644
>> --- a/FAQ
>> +++ b/FAQ
>> @@ -1124,6 +1124,12 @@ A: Do you have a c
On Wed, Jun 25, 2014 at 11:07:31AM +0900, YAMAMOTO Takashi wrote:
> Signed-off-by: YAMAMOTO Takashi
> ---
> FAQ | 6 ++
> 1 file changed, 6 insertions(+)
>
> diff --git a/FAQ b/FAQ
> index 79d905d..c2520fc 100644
> --- a/FAQ
> +++ b/FAQ
> @@ -1124,6 +1124,12 @@ A: Do you have a controller co
These two cases used to be treated differently for IPv4/IPv6, but they
are now identical.
Signed-off-by: Joe Stringer
---
datapath/flow_netlink.c | 13 +++--
1 file changed, 3 insertions(+), 10 deletions(-)
diff --git a/datapath/flow_netlink.c b/datapath/flow_netlink.c
index 5a978f0..
The original message was received at Thu, 26 Jun 2014 09:46:13 +0700
from openvswitch.org [90.199.9.180]
- The following addresses had permanent fatal errors -
dev@openvswitch.org
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org
On Wed, Jun 25, 2014 at 5:04 PM, Ben Pfaff wrote:
> On Tue, Jun 10, 2014 at 2:06 PM, Alessandro Pilotti
> wrote:
>> https://github.com/cloudbase/openvswitch-hyperv
>> https://github.com/cloudbase/openvswitch-hyperv-kernel
>
> Thanks a lot for sending this out. I've just now started taking a
> fi
On Tue, Jun 10, 2014 at 2:06 PM, Alessandro Pilotti
wrote:
> https://github.com/cloudbase/openvswitch-hyperv
> https://github.com/cloudbase/openvswitch-hyperv-kernel
Thanks a lot for sending this out. I've just now started taking a
first look at it.
I see that there are 216 commits beyond the b
On Mon, Jun 23, 2014 at 05:34:59PM -0700, Saurabh Shah wrote:
> With this implementation we support bridge backed forwarding (with VLAN
> tagging)
> & tunneling over VXLAN.
>
> Co-Authored-By: Eitan Eliahu
> Signed-off-by: Eitan Eliahu
> Co-Authored-By: Guolin Yang
> Signed-off-by: Guolin Yang
On Mon, Jun 23, 2014 at 05:34:58PM -0700, Saurabh Shah wrote:
> Co-Authored-By: Eitan Eliahu
> Signed-off-by: Eitan Eliahu
> Co-Authored-By: Guolin Yang
> Signed-off-by: Guolin Yang
> Co-Authored-By: Linda Sun
> Signed-off-by: Linda Sun
> Co-Authored-By: Nithin Raju
> Signed-off-by: Nithin R
On Wed, Jun 25, 2014 at 02:19:38PM -0700, Ben Pfaff wrote:
> On Tue, Jun 24, 2014 at 08:46:30AM +0900, Simon Horman wrote:
> > The motivation of this series is to allow some sequences of actions
> > that include MPLS actions to be performed using recirculation.
> > Sequences of actions that could n
On Thu, Jun 19, 2014 at 3:58 PM, Polehn, Mike A wrote:
> Large TX and RX queues are needed for high speed 10 GbE physical NICS.
> Observed a 250% zero loss improvement over small NIC queue test for
> A port to port flow test.
>
> Signed-off-by: Mike A. Polehn
I am fine with the
>
> diff --git a/l
On Wed, Jun 25, 2014 at 11:02 AM, Ben Pfaff wrote:
> Signed-off-by: Ben Pfaff
> ---
> lib/dpif.c | 17 +
> 1 file changed, 17 insertions(+)
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailma
On Wed, Jun 25, 2014 at 11:02 AM, Ben Pfaff wrote:
> This should make it easier to identify problems that result from bugs in
> the execution helper.
>
> Suggested-by: Jesse Gross
> Signed-off-by: Ben Pfaff
Acked-by: Jesse Gross
___
dev mailing list
On Wed, Jun 25, 2014 at 11:02 AM, Ben Pfaff wrote:
> Only dpif_execute() was checking for oversized actions but dpif_operate()
> should do so also. This fixes the problem.
>
> Found by inspection.
>
> Signed-off-by: Ben Pfaff
Acked-by: Jesse Gross
__
On 24.06.2014, at 03:55, "Justin Pettit"
mailto:jpet...@nicira.com>> wrote:
On Sun, Jun 22, 2014 at 5:42 PM, Alessandro Pilotti
mailto:apilo...@cloudbasesolutions.com>> wrote:
In addition to the code repositories made previously available, here’s a wiki
document describing our OVS Hyper-V po
On Jun 25, 2014, at 3:02 PM, Pravin Shelar wrote:
> On Wed, Jun 25, 2014 at 11:39 AM, Daniele Di Proietto
> wrote:
>> This commit fixes memory leaks in dp_execute_cb() in two cases:
>>- when the output port cannot be found
>>- when the recirculation depth is exceeded
>>
>> Reported-by:
On Wed, Jun 25, 2014 at 02:57:34PM -0700, Ben Pfaff wrote:
> On Mon, Jun 23, 2014 at 05:34:56PM -0700, Saurabh Shah wrote:
> > This is the "Hyper-V Extensible Switch extension filter driver" sample code
> > available at:
> > http://code.msdn.microsoft.com/windowshardware/Hyper-V-Extensible-Virtual-
On Mon, Jun 23, 2014 at 05:34:57PM -0700, Saurabh Shah wrote:
> These are some minimal changes required to get the base code to work with our
> forwarding extension. These changes are licensed under Apache License, Version
> 2.0.
>
> Co-Authored-By: Eitan Eliahu
> Signed-off-by: Eitan Eliahu
> C
On Wed, Jun 25, 2014 at 11:39 AM, Daniele Di Proietto
wrote:
> This commit fixes memory leaks in dp_execute_cb() in two cases:
> - when the output port cannot be found
> - when the recirculation depth is exceeded
>
> Reported-by: Pravin Shelar
> Signed-off-by: Daniele Di Proietto
> ---
T
On Mon, Jun 23, 2014 at 05:34:56PM -0700, Saurabh Shah wrote:
> This is the "Hyper-V Extensible Switch extension filter driver" sample code
> available at:
> http://code.msdn.microsoft.com/windowshardware/Hyper-V-Extensible-Virtual-e4b31fbb
>
> The sample code is licensed under Microsoft Limited P
Thanks, pushed with suggested changes.
On Wed, Jun 25, 2014 at 1:21 PM, Pravin Shelar wrote:
> On Mon, Jun 23, 2014 at 11:10 PM, Andy Zhou wrote:
>> Sparse gives "incompatible types in comparison expression (different
>> address spaces)" warning messages. Fix this by add rcu_dereference()
>> wra
On Tue, Jun 24, 2014 at 08:46:30AM +0900, Simon Horman wrote:
> The motivation of this series is to allow some sequences of actions
> that include MPLS actions to be performed using recirculation.
> Sequences of actions that could not previously be handled.
>
> For example pop_mpls:0x0800,dec_ttl.
Thanks, applied to master.
On Wed, Jun 25, 2014 at 01:52:32PM -0700, Alex Wang wrote:
> Acked-by: Alex Wang
>
>
> On Wed, Jun 25, 2014 at 1:44 PM, Ben Pfaff wrote:
>
> > I thought this was in here already, but I guess not.
> >
> > Signed-off-by: Ben Pfaff
> > ---
> > CodingStyle |5
On Wed, Jun 25, 2014 at 01:53:51PM -0700, Alex Wang wrote:
> Yes, Thomas also pointed it out in V2,
>
> Will fix it.
Thanks.
> Also, remind me to clean up my patches in patchwork...
It looked like this series needed a v2 so I marked all of them as
Changes Requested (even though some of them may
Yes, Thomas also pointed it out in V2,
Will fix it.
Also, remind me to clean up my patches in patchwork...
Thanks,
On Wed, Jun 25, 2014 at 1:51 PM, Ben Pfaff wrote:
> On Mon, Jun 23, 2014 at 12:37:29PM -0700, Alex Wang wrote:
> > diff --git a/lib/netdev-dpdk.h b/lib/netdev-dpdk.h
> > index
Acked-by: Alex Wang
On Wed, Jun 25, 2014 at 1:44 PM, Ben Pfaff wrote:
> I thought this was in here already, but I guess not.
>
> Signed-off-by: Ben Pfaff
> ---
> CodingStyle |5 +
> 1 file changed, 5 insertions(+)
>
> diff --git a/CodingStyle b/CodingStyle
> index 0ba0366..628f21f 10
On Mon, Jun 23, 2014 at 12:37:29PM -0700, Alex Wang wrote:
> diff --git a/lib/netdev-dpdk.h b/lib/netdev-dpdk.h
> index f443a21..da507ce 100644
> --- a/lib/netdev-dpdk.h
> +++ b/lib/netdev-dpdk.h
> @@ -20,13 +20,18 @@ struct dpif_packet;
> #include
> #include
>
> +struct netdev;
I think that
On Fri, Jun 20, 2014 at 10:24:33PM +, Polehn, Mike A wrote:
> Put in a DPDK queue to receive from multiple core SMP input from vSwitch for
> NIC TX output.
> Eliminated the inside polling loop SMP TX output lock (DPDK queue handles
> SMP).
> Added a SMP lock for non-polling operation to allow
I thought this was in here already, but I guess not.
Signed-off-by: Ben Pfaff
---
CodingStyle |5 +
1 file changed, 5 insertions(+)
diff --git a/CodingStyle b/CodingStyle
index 0ba0366..628f21f 100644
--- a/CodingStyle
+++ b/CodingStyle
@@ -162,6 +162,11 @@ such a function (including th
On Wed, Jun 25, 2014 at 01:05:17PM -0700, Ryan Wilson wrote:
> miniflow_destroy() needs to be called after using miniflow_init().
> Otherwise, if the miniflow mallocs data, then a memory leak may
> occur.
>
> Found by inspection.
>
> Signed-off-by: Ryan Wilson
Thanks, applied to master and bran
On Mon, Jun 23, 2014 at 11:10 PM, Andy Zhou wrote:
> Sparse gives "incompatible types in comparison expression (different
> address spaces)" warning messages. Fix this by add rcu_dereference()
> wrappers.
>
> Reported-by: Ben Pfaff
> Signed-off-by: Andy Zhou
> ---
> datapath/flow_table.c | 6 ++
Hi Saurabh,
Thanks for posting these patches!
We looked at the code in the last two days, running various tests and did
comparisons with our porting. We tried to be as unbiased as possible in
the review, with the goal of making the best out of both codebases and not a
“us” vs “them” match. :)
Fo
miniflow_destroy() needs to be called after using miniflow_init().
Otherwise, if the miniflow mallocs data, then a memory leak may
occur.
Found by inspection.
Signed-off-by: Ryan Wilson
---
lib/dpif-netdev.c |1 +
1 file changed, 1 insertion(+)
diff --git a/lib/dpif-netdev.c b/lib/dpif-net
Thanks
On Jun 25, 2014, at 10:56 AM, Pravin Shelar wrote:
> On Wed, Jun 25, 2014 at 2:55 AM, Thomas Graf wrote:
>> On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
>>> We do not use any offloading (now) or multiple segments per packet, so
>>> we might as well disable those features while confi
Thanks
On Jun 25, 2014, at 10:55 AM, Pravin Shelar wrote:
> On Wed, Jun 25, 2014 at 2:55 AM, Thomas Graf wrote:
>> On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
>>> Signed-off-by: Daniele Di Proietto
>>
>> Acked-by: Thomas Graf
>
> I pushed it to master.
>
> Thanks
___
Thanks
On Jun 25, 2014, at 10:55 AM, Pravin Shelar wrote:
> On Wed, Jun 25, 2014 at 2:49 AM, Thomas Graf wrote:
>> On 06/24/14 at 04:04pm, Daniele Di Proietto wrote:
>>> Commit f4fd623c4c25 introduced a bug in netdev_dpdk_send(): if multiple
>>> consecutive packets exceed MTU, only the first one
>
>
> Thanks Ryan!
>
> I folded in this change to ensure that the caller could specify any
> 'max_flows' that it likes. It doesn't make sense for the caller to
> have to be aware of the implementation's limitations:
>
>
I was debating between either using an assert or using the min of max_flows
an
On Mon, Jun 23, 2014 at 12:36:11PM -0700, Ryan Wilson wrote:
> Previously, flows were retrieved one by one when dumping flows for
> datapaths of type 'netdev'. This increased contention for the dump's
> mutex, negatively affecting revalidator performance.
>
> This patch retrieves batches of flows
Thanks, applied to master.
On Wed, Jun 25, 2014 at 11:44:09AM -0700, Justin Pettit wrote:
> Acked-by: Justin Pettit
>
> --Justin
>
>
> > On Jun 24, 2014, at 2:46 PM, Ben Pfaff wrote:
> >
> > The syntax is inconvenient but at least it's documented.
> >
> > Signed-off-by: Ben Pfaff
> > ---
>
On Wed, Jun 25, 2014 at 11:09 AM, Ben Pfaff wrote:
> I am really surprised to hear that it takes over a minute. On my
> workstation (which is a few years old), "ovstest test-cmap check 1"
> only takes 6.5 seconds. Do you have any idea what's different on
> XenServer? It might be the GCC version
This commit fixes memory leaks in dp_execute_cb() in two cases:
- when the output port cannot be found
- when the recirculation depth is exceeded
Reported-by: Pravin Shelar
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 11 ++-
1 file changed, 10 insertions(+), 1 del
Thanks for the review.
I applied this to master, branch-2.{0,1,2,3}, and branch-1.{4,9,11}.
On Wed, Jun 25, 2014 at 11:05:56AM -0700, Alex Wang wrote:
> Looks good to me,
>
> Acked-by: Alex Wang
>
> Thx,
>
>
> On Tue, Jun 24, 2014 at 5:06 PM, Ben Pfaff wrote:
>
> > json_string_unescape() f
Acked-by: Justin Pettit
--Justin
> On Jun 24, 2014, at 2:46 PM, Ben Pfaff wrote:
>
> The syntax is inconvenient but at least it's documented.
>
> Signed-off-by: Ben Pfaff
> ---
> utilities/ovs-ofctl.8.in |3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/utilities
Thanks, applied to master.
On Wed, Jun 25, 2014 at 06:15:12PM +, Pritesh Kothari (pritkoth) wrote:
> Acked-by: Pritesh Kothari
>
> On Jun 25, 2014, at 10:59 AM, Ben Pfaff wrote:
>
> > Signed-off-by: Ben Pfaff
> > ---
> > lib/dpif-linux.c |4 ++--
> > 1 file changed, 2 insertions(+), 2
On Wed, Jun 25, 2014 at 04:15:54AM -0700, Jarno Rajahalme wrote:
> Factor out the priority vector code from the classifier.
>
> Making the classifier use RCU instead of locking requires parallel
> access to the priority vector, pointing to subtables in descending
> priority order. When a new subt
Acked-by: Pritesh Kothari
On Jun 25, 2014, at 10:59 AM, Ben Pfaff wrote:
> Signed-off-by: Ben Pfaff
> ---
> lib/dpif-linux.c |4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/lib/dpif-linux.c b/lib/dpif-linux.c
> index 66911c7..0eac3e7 100644
> --- a/lib/dpif-linu
I am really surprised to hear that it takes over a minute. On my
workstation (which is a few years old), "ovstest test-cmap check 1"
only takes 6.5 seconds. Do you have any idea what's different on
XenServer? It might be the GCC version, which version is it using?
On Wed, Jun 25, 2014 at 09:40:
Sounds good. I'll look at the pvector v2 now.
On Wed, Jun 25, 2014 at 04:19:23AM -0700, Jarno Rajahalme wrote:
> Ben,
>
> Thanks for the reviews!
>
> I have addressed the (minor) comments on the series, will push once the
> vector v2 is ack?ed. I?ll keep this last patch as the first in the cla
Looks good to me,
Acked-by: Alex Wang
Thx,
On Tue, Jun 24, 2014 at 5:06 PM, Ben Pfaff wrote:
> json_string_unescape() flagged a backslash at the end of a string as an
> error, but of course "\\" is a valid string. This fixes the problem.
>
> VMware-BZ: #1275208
> Reported-by: Michael Hu
>
Thanks!
This series has dragged on a while so I'll try to expedite review.
On Wed, Jun 25, 2014 at 03:58:00AM -0700, Jarno Rajahalme wrote:
> Thanks for the review. I have addressed all the comments, there is
> quite a nice additional clean-up in classifier_lookup(). In addition
> to the lookahea
On Tue, Jun 24, 2014 at 05:19:02PM -0700, Ben Pfaff wrote:
> > Maybe we also need a log message lower down in the stack showing what
> > is actually being sent to the kernel in these cases?
>
> I agree, I'm thinking about that too.
I sent out a short series:
http://openvswitch.org/piperma
This should make it easier to identify problems that result from bugs in
the execution helper.
Suggested-by: Jesse Gross
Signed-off-by: Ben Pfaff
---
lib/dpif.c | 17 -
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/lib/dpif.c b/lib/dpif.c
index 2e98de2..dcd60a
Only dpif_execute() was checking for oversized actions but dpif_operate()
should do so also. This fixes the problem.
Found by inspection.
Signed-off-by: Ben Pfaff
---
lib/dpif.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/lib/dpif.c b/lib/dpif.c
index 19
Signed-off-by: Ben Pfaff
---
lib/dpif.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/lib/dpif.c b/lib/dpif.c
index dcd60a5..2b6f36d 100644
--- a/lib/dpif.c
+++ b/lib/dpif.c
@@ -1554,6 +1554,23 @@ log_flow_del_message(struct dpif *dpif, const struct
dpif_flow_del *del,
Signed-off-by: Ben Pfaff
---
lib/dpif-linux.c |4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/dpif-linux.c b/lib/dpif-linux.c
index 66911c7..0eac3e7 100644
--- a/lib/dpif-linux.c
+++ b/lib/dpif-linux.c
@@ -1362,9 +1362,9 @@ dpif_linux_execute(struct dpif *dpif_, str
On Tue, Jun 24, 2014 at 4:08 PM, Daniele Di Proietto
wrote:
> In dp_netdev_input() we nevered fully covered the case where handler queues
> are
> not there.
> With this change we increment the stat counter and free the packet.
>
> Signed-off-by: Daniele Di Proietto
LGTM,
Pushed to master.
Than
On Wed, Jun 25, 2014 at 2:55 AM, Thomas Graf wrote:
> On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
>> Signed-off-by: Daniele Di Proietto
>
> Acked-by: Thomas Graf
I pushed it to master.
Thanks.
___
dev mailing list
dev@openvswitch.org
http://op
On Wed, Jun 25, 2014 at 2:55 AM, Thomas Graf wrote:
> On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
>> We do not use any offloading (now) or multiple segments per packet, so
>> we might as well disable those features while configuring the NIC.
>>
>> This could give performance improvements. F
On Wed, Jun 25, 2014 at 2:49 AM, Thomas Graf wrote:
> On 06/24/14 at 04:04pm, Daniele Di Proietto wrote:
>> Commit f4fd623c4c25 introduced a bug in netdev_dpdk_send(): if multiple
>> consecutive packets exceed MTU, only the first one is deleted and
>> counted.
>>
>> This should fix the bug
>>
>> S
On Wed, Jun 25, 2014 at 10:48:41AM +, Tahhan, Maryam wrote:
> Thanks for the feedback, I will refactor and resubmit, just a
> question regarding the section that sets the MAC address for the
> logical vhost port, is the issue just the formatting you mention
> after the comment about it being wr
On Wed, Jun 25, 2014 at 11:05:56AM +0200, Thomas Graf wrote:
> On 06/24/14 at 04:40pm, Ben Pfaff wrote:
> > Open vSwitch userspace is able to implement some actions that the kernel
> > doesn't support, such as modifying ARP fields. When it does this for a
> > tunneled packet, it needs to supply th
I had a quick comment. I noticed while running unit tests on Xenserver
that the cuckoo hash unit test was very slow. It takes a little more
than one minute to complete. I wonder whether using more cmap would
hurt Xenserver's performance?
On Wed, Jun 25, 2014 at 4:19 AM, Jarno Rajahalme wrote:
> B
On Tue, Jun 24, 2014 at 2:20 PM, Daniele Di Proietto
wrote:
> On Jun 8, 2014, at 1:18 PM, Pravin B Shelar wrote:
>
>> dpif-packet contains ofpbuf which points to packet data. Here buf
>> is better name rather than ofp.
>> Following patch renames all remaining instances of ofp variable.
>>
>> Sig
On 6/25/14, 5:19 AM, Jesse Gross wrote:
On Wed, Jun 18, 2014 at 9:45 PM, Jesse Gross wrote:
On Tue, Jun 17, 2014 at 12:21 PM, Lori Jakab wrote:
Hi Jesse,
On 5/23/14, 2:07 AM, Jesse Gross wrote:
On Tue, May 20, 2014 at 9:27 PM, Lori Jakab wrote:
On 5/21/14, 4:10 AM, Jesse Gross wrote:
On
On 06/25/14 at 08:54am, Alex Wang wrote:
> > index 85ecc5c..77b9b39 100644
>
> > > --- a/tests/ofproto-macros.at
> > > +++ b/tests/ofproto-macros.at
> > > @@ -76,6 +76,7 @@ m4_define([OVS_VSWITCHD_START],
> > > AT_CHECK([ovs-vswitchd --detach --no-chdir --pidfile
> > --enable-dummy$3 --disable
On Wed, Jun 25, 2014 at 2:59 AM, Thomas Graf
wrote:
> On 06/24/14 at 06:40pm, Alex Wang wrote:
> > Signed-off-by: Alex Wang
> > ---
> > PATCH -> V2:
> > - Rebase.
>
> LGTM, minor nitpick below.
>
> Acked-by: Thomas Graf
>
> > diff --git a/lib/netdev-dpdk.h b/lib/netdev-dpdk.h
> > index f443a21.
> index 85ecc5c..77b9b39 100644
> > --- a/tests/ofproto-macros.at
> > +++ b/tests/ofproto-macros.at
> > @@ -76,6 +76,7 @@ m4_define([OVS_VSWITCHD_START],
> > AT_CHECK([ovs-vswitchd --detach --no-chdir --pidfile
> --enable-dummy$3 --disable-system --log-file -vvconn -vofproto_dpif], [0],
> [],
On Wed, Jun 25, 2014 at 1:30 AM, Thomas Graf wrote:
> On 06/24/14 at 06:46pm, Jesse Gross wrote:
>> Currently, if the network stack provides skb->rxhash then we use it,
>> otherwise we compute our own. However, on at least some versions of
>> RHEL/CentOS, the stack provides a hash but it is 16 bit
Ben,
Thanks for the reviews!
I have addressed the (minor) comments on the series, will push once the vector
v2 is ack’ed. I’ll keep this last patch as the first in the classifier RCU
series.
Jarno
On Jun 13, 2014, at 10:37 AM, Ben Pfaff wrote:
> On Mon, Jun 09, 2014 at 11:53:55AM -0700, J
Factor out the priority vector code from the classifier.
Making the classifier use RCU instead of locking requires parallel
access to the priority vector, pointing to subtables in descending
priority order. When a new subtable is added, a new copy of the
priority vector is allocated, while the cu
Thanks for the review. I have addressed all the comments, there is quite a nice
additional clean-up in classifier_lookup(). In addition to the lookahead, I
also integrated the priority handling to an iterator. Will send v2 right away.
Jarno
On Jun 13, 2014, at 10:06 AM, Ben Pfaff wrote:
> O
Hi Ben
Thanks for the feedback, I will refactor and resubmit, just a question
regarding the section that sets the MAC address for the logical vhost port, is
the issue just the formatting you mention after the comment about it being
wrong or was there an issue with setting the MAC to something li
On 06/24/14 at 06:40pm, Alex Wang wrote:
> Signed-off-by: Alex Wang
> ---
> PATCH -> V2:
> - Rebase.
LGTM, minor nitpick below.
Acked-by: Thomas Graf
> diff --git a/lib/netdev-dpdk.h b/lib/netdev-dpdk.h
> index f443a21..da507ce 100644
> --- a/lib/netdev-dpdk.h
> +++ b/lib/netdev-dpdk.h
> @@ -2
On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
> Signed-off-by: Daniele Di Proietto
Acked-by: Thomas Graf
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On 06/24/14 at 04:05pm, Daniele Di Proietto wrote:
> We do not use any offloading (now) or multiple segments per packet, so
> we might as well disable those features while configuring the NIC.
>
> This could give performance improvements. For ixgbe, for example, this change
> allows the driver to
On 06/24/14 at 04:04pm, Daniele Di Proietto wrote:
> Commit f4fd623c4c25 introduced a bug in netdev_dpdk_send(): if multiple
> consecutive packets exceed MTU, only the first one is deleted and
> counted.
>
> This should fix the bug
>
> Signed-off-by: Daniele Di Proietto
Acked-by: Thomas Graf
_
On 06/24/14 at 06:40pm, Alex Wang wrote:
> Signed-off-by: Alex Wang
>
> ---
> PATCH -> V2:
> - Use readdir_r() instead of readdir() for reentrency.
> - Address review comments from Thomas Graf.
> - Add dummy interface for WIN32 case.
One minor comment below.
> index 85ecc5c..77b9b39 100644
> --
On Mon, Jun 23, 2014 at 05:14:52PM -0700, Ben Pfaff wrote:
> On Mon, Jun 16, 2014 at 11:29:30AM +0900, Simon Horman wrote:
> > Handle modify and delete commands in OpenFlow1.4 flow monitor requests.
> > These commands are not yet allowed by the decoder which
> > will be updated by a subsequent patc
On 06/24/14 at 04:40pm, Ben Pfaff wrote:
> Open vSwitch userspace is able to implement some actions that the kernel
> doesn't support, such as modifying ARP fields. When it does this for a
> tunneled packet, it needs to supply the tunnel information with a "set"
> action, because the Linux kernel
On 06/24/14 at 06:46pm, Jesse Gross wrote:
> Currently, if the network stack provides skb->rxhash then we use it,
> otherwise we compute our own. However, on at least some versions of
> RHEL/CentOS, the stack provides a hash but it is 16 bits rather than
> 32 bits. In cases where we use the upper m
On Mon, Jun 23, 2014 at 03:16:59PM -0700, Ben Pfaff wrote:
> On Mon, Jun 16, 2014 at 11:29:22AM +0900, Simon Horman wrote:
> > If the ONLY_OWN flag of a flow monitor is set then ofmonitor_report should
> > skip sending updates to other controllers.
> >
> > This is in preparation for supporting Ope
80 matches
Mail list logo
