This patch series adds support for custom VXLAN tunnel port and for multiple
VXLAN tunnels. Because adding/removing tunnel ports is a time-consuming
process, the Netlink library was modified to support asynchronous transactions
as well.
Sorin Vinturis (4):
[PATCH v5 1/4] datapath-windows: Sup
At the moment the OVS extension supports only one VXLAN tunnel that
is cached in the extension switch context. Replaced the latter
cached pointer with an array list that contains all VXLAN tunnel
vports.
Signed-off-by: Sorin Vinturis
Reported-by: Alin Gabriel Serdean
Reported-at: https://github.
Modified 'nl_sock_transact_multiple__' function to send asynchronous
I/O requests to the kernel driver.
Signed-off-by: Sorin Vinturis
Reported-by: Alin Gabriel Serdean
Reported-at: https://github.com/openvswitch/ovs-issues/issues/64
---
v5: No changes compared to previous version.
---
lib/netli
The kernel datapath supports only port 4789 for VXLAN tunnel creation.
Added support in order to allow for the VXLAN tunnel port to be
configurable to any port number set by the userspace.
The patch also checks to see if an existing WFP filter, for the
necessary UDP tunnel port, is already created
Signed-off-by: Sorin Vinturis
Acked-by: Nithin Raju
---
datapath-windows/ovsext/TunnelFilter.c | 225 -
1 file changed, 221 insertions(+), 4 deletions(-)
diff --git a/datapath-windows/ovsext/TunnelFilter.c
b/datapath-windows/ovsext/TunnelFilter.c
index 0dedca2..
Added support for creating and handling multiple NBLs with only one NB
for ingress data path.
Signed-off-by: Sorin Vinturis
Reported-by: Alessandro Pilotti
Reported-at: https://github.com/openvswitch/ovs-issues/issues/2
---
v2: Original NBL's buffer context reference count is modified through
Ov
On Tue, May 19, 2015 at 02:29:45PM -0700, Alex Wang wrote:
> This commit changes the type of 'chassis' column in 'Binding' table
> from string to weak reference of 'Chassis' table entry. This will
> make accessing the chassis from binding more efficient.
>
> Signed-off-by: Alex Wang
This code s
This patch adds support for a new port type to the userspace
datapath called dpdkvhostuser.
A new dpdkvhostuser port will create a unix domain socket which
when provided to QEMU is used to facilitate communication between
the virtio-net device on the VM and the OVS port on the host.
vhost-cuse ('
Thanks for fixing this!
I've tested it with different flow tables and it doesn't appear to have
any performance penalty at all
Acked-by: Daniele Di Proietto
On 21/05/2015 01:06, "Ethan Jackson" wrote:
>When executing actions, it's possible a recirculation will occur
>causing dp_netdev_input(
I totally agree with the suggested change. Should the need arise,
we could make it configurable later.
Acked-by: Daniele Di Proietto
On 13/05/2015 14:54, "Ciara Loftus" wrote:
>Prior to this commit, the number of possible entries in the Exact
>Match Cache stood at 1024 per thread exacting to
This seems a really nice improvement to me. Thanks!
Unfortunately the patch doesn't apply anymore, could you
rebase and include my ack?
Acked-by: Daniele Di Proietto
On 19/05/2015 22:11, "Kevin Traynor" wrote:
>This patch simplifies Rx/Tx NIC configuration by removing
>custom values and using
This patch simplifies Rx/Tx NIC configuration by removing
custom values and using the defaults provided by the DPDK
PMDs. This also enables Rx vectorisation which improves
performance.
v2: rebase to master
Signed-off-by: Kevin Traynor
Acked-by: Daniele Di Proietto
---
lib/netdev-dpdk.c | 32
> -Original Message-
> From: Daniele Di Proietto [mailto:diproiet...@vmware.com]
> Sent: Thursday, May 21, 2015 4:55 PM
> To: Traynor, Kevin
> Cc: dev@openvswitch.org
> Subject: Re: [ovs-dev] [PATCH] netdev-dpdk: Use default NIC configuration.
>
> This seems a really nice improvement to m
This commit changes the type of 'chassis' column in 'Binding' table
from string to weak reference of 'Chassis' table entry. This will
make accessing the chassis from binding more efficient.
Signed-off-by: Alex Wang
Acked-by: Ben Pfaff
---
PATCH->V2:
- Add helper function for getting chassis by
How about adding an inline function like this?~
On Thu, May 21, 2015 at 10:04 AM, Alex Wang wrote:
> This commit changes the type of 'chassis' column in 'Binding' table
> from string to weak reference of 'Chassis' table entry. This will
> make accessing the chassis from binding more efficient.
hi Sorin,
Thanks for the respin.
I had 2 comments in the previous review regarding access to a freed up ‘vport’
in OvsDeleteVportCmdHandler() and OvsTunnelVportPendingUninit().
It looks like you addressed the issue with OvsTunnelVportPendingUninit(), by
making sure that the Vport is not dealloc
Hi,
currently, ovs switches LRO off in user space:
commit 24b019f808211a95078efd916064af0975ca5733
Author: Justin Pettit
Date: Fri Aug 26 23:34:40 2011 -0700
datapath: Disable LRO from userspace instead of the kernel.
Whenever a port is added to the datapath, LRO is automatically
> On May 21, 2015, at 4:30 AM, Sorin Vinturis
> wrote:
>
> Modified 'nl_sock_transact_multiple__' function to send asynchronous
> I/O requests to the kernel driver.
>
> Signed-off-by: Sorin Vinturis
> Reported-by: Alin Gabriel Serdean
> Reported-at:
> https://urldefense.proofpoint.com/v2/url
On Wed, May 20, 2015 at 01:22:18PM -0700, Ethan Jackson wrote:
> Hey guys,
>
> I know this is a super old thread, but is there any interest in
> reviving it? On our end we've had a terrible time getting ivshmem
> working until we found this documentation. I expect future users will
> have the sa
Nithin,
I thought I have addressed your comment. My understanding was that was an issue
in OvsDeleteVportCmdHandler() after the call to OvsRemoveAndDeleteVport(). The
latter function might deallocate the vport, which would be used by the
OvsTunnelVportPendingUninit() callback. I have modified
Daniele/Vasmi,
You were the last two on our end to stand up ivshmem. Would you mind
resubmitting this patch with whatever tweaks you needed to make it
work?
Ethan
On Thu, May 21, 2015 at 12:41 PM, Flavio Leitner wrote:
> On Wed, May 20, 2015 at 01:22:18PM -0700, Ethan Jackson wrote:
>> Hey guy
Thanks, I've merged.
On Thu, May 21, 2015 at 1:44 PM, Pravin Shelar wrote:
> On Wed, May 20, 2015 at 5:06 PM, Ethan Jackson wrote:
>> When executing actions, it's possible a recirculation will occur
>> causing dp_netdev_input() to be called multiple times. If the batch
>> pointers embedded in d
On Thu, May 21, 2015 at 10:37 AM, Jiri Benc wrote:
> Hi,
>
> currently, ovs switches LRO off in user space:
>
> commit 24b019f808211a95078efd916064af0975ca5733
> Author: Justin Pettit
> Date: Fri Aug 26 23:34:40 2011 -0700
>
> datapath: Disable LRO from userspace instead of the kernel.
>
>
Reported-by: Gurucharan Shetty
Signed-off-by: Joe Stringer
---
tests/ofproto-dpif.at | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tests/ofproto-dpif.at b/tests/ofproto-dpif.at
index 3361dc2..1459ea2 100644
--- a/tests/ofproto-dpif.at
+++ b/tests/ofproto-dpif.at
@@ -4155,7
It's useful to distinguish which type of flow that the parser thinks it
is parsing when we output error messages.
Signed-off-by: Joe Stringer
---
ofproto/ofproto-dpif.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/ofproto/ofproto-dpif.c b/ofproto/ofproto-dpif.c
index d
Signed-off-by: Joe Stringer
---
lib/odp-util.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/lib/odp-util.c b/lib/odp-util.c
index 962b84b..e402888 100644
--- a/lib/odp-util.c
+++ b/lib/odp-util.c
@@ -2714,6 +2714,17 @@ static int
parse_odp_key_mask_attr(const char *s, const s
Signed-off-by: Joe Stringer
---
tests/ofproto-dpif.at | 48
1 file changed, 48 insertions(+)
diff --git a/tests/ofproto-dpif.at b/tests/ofproto-dpif.at
index 1459ea2..a7daddf 100644
--- a/tests/ofproto-dpif.at
+++ b/tests/ofproto-dpif.at
@@ -4402,
This commit adds appctl support to ovn-northd and the 'exit' command.
The 'exit' command can be used in autotest for stopping the ovn-northd.
Signed-off-by: Alex Wang
---
ovn/northd/ovn-northd.c | 35 +--
1 file changed, 33 insertions(+), 2 deletions(-)
diff --
Send me a F#ckFriends request so we can hook up
My usename is VeronicaWet09
http://hop.kz/dobF";>my profile is here TALK S00N
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Wed, May 20, 2015 at 5:06 PM, Ethan Jackson wrote:
> When executing actions, it's possible a recirculation will occur
> causing dp_netdev_input() to be called multiple times. If the batch
> pointers embedded in dp_netdev_flow aren't cleared, it's possible
> packets after the recirculation will
Applied, thanks!
On Thu, May 21, 2015 at 9:26 AM, Kevin Traynor wrote:
> This patch simplifies Rx/Tx NIC configuration by removing
> custom values and using the defaults provided by the DPDK
> PMDs. This also enables Rx vectorisation which improves
> performance.
>
> v2: rebase to master
>
> Sign
Applied, thanks!
Ethan
On Thu, May 21, 2015 at 8:38 AM, Daniele Di Proietto
wrote:
> I totally agree with the suggested change. Should the need arise,
> we could make it configurable later.
>
> Acked-by: Daniele Di Proietto
>
> On 13/05/2015 14:54, "Ciara Loftus" wrote:
>
>>Prior to this comm
OVS kernel module support for masked set actions in already upstream
in Linux. This patch adds the same for the OVS tree kernel module.
The existing set action sets many fields at once. When only a subset
of the IP header fields, for example, should be modified, all the IP
fields need to be exac
> As a consequence, this requires dropping support for old versions of
> XenServer. I don't expect that to be much of a problem.
Unfortunately, the most recent release of XenServer (6.5) still ships
with Python 2.4.
> +Open vSwitch requires a version of XenServer (XCP) that includes a
> +modern
On Thu, May 21, 2015 at 4:39 PM, Jarno Rajahalme wrote:
> OVS kernel module support for masked set actions in already upstream
> in Linux. This patch adds the same for the OVS tree kernel module.
>
> The existing set action sets many fields at once. When only a subset
> of the IP header fields,
35 matches
Mail list logo