On Thu, Oct 27, 2016 at 09:45:42PM +, Alin Serdean wrote:
> Skip symlinks checks on Windows.
>
> Signed-off-by: Alin Gabriel Serdean
Applied, thanks!
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Tue, Nov 01, 2016 at 08:26:06PM -0700, Ben Pfaff wrote:
> +/* Replace original file by the temporary file.
> + *
> + * We support two strategies:
> + *
> + * - The preferred strategy is to rename the temporary file over the
> + * original one in-place, then clos
On Thu, Oct 27, 2016 at 09:45:42PM +, Alin Serdean wrote:
> This patch allows online compacting to be done under Windows.
>
> To achieve the above we need to close all file handles before trying to
> rename the file, switch from rename to MoveFileEx (because rename/MoveFile
> fails if the dest
The Open vSwitch team will host our third annual conference focused on Open
vSwitch and OVN on Nov. 7 and 8, 2016, to be held at the San Jose Doubletree.
The schedule is finalized and available here:
https://events.linuxfoundation.org/events/open-vswitch-2016-fall-conference/program/agenda
On Tue, Nov 01, 2016 at 03:44:13PM -0700, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Tue, Nov 01, 2016 at 03:44:12PM -0700, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
Signed-off-by: Justin Pettit
---
NEWS | 4
configure.ac | 2 +-
debian/changelog | 8
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/NEWS b/NEWS
index 4c1f391..9970297 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,7 @@
+v2.6.2 - xx xxx
+---
Signed-off-by: Justin Pettit
---
NEWS | 3 ++-
debian/changelog | 6 --
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/NEWS b/NEWS
index 4326107..4c1f391 100644
--- a/NEWS
+++ b/NEWS
@@ -1,7 +1,8 @@
-v2.6.1 - xx xxx
+v2.6.1 - 01 Nov 2016
-
On Thu, Oct 27, 2016 at 08:33:35PM +, Alin Serdean wrote:
> This patch adds the offline compacting (ovsdb-tool compact) to be run on
> Windows.
>
> On Windows we are missing "--run" so in return we start ovsdb-server,
> run the ovsdb-client dump command and after issue a command to the
> ovsdb
> On Nov 1, 2016, at 12:09 PM, Pravin Shelar wrote:
>
> On Mon, Oct 31, 2016 at 1:30 PM, Justin Pettit wrote:
>>
>>> On Oct 31, 2016, at 6:10 AM, Richard Theis wrote:
>>>
So, it turns out my fix does not introduce any new problems. I have
just posted
it, so consider if you wan
On Fri, Oct 21, 2016 at 07:00:22PM -0500, Flavio Fernandes wrote:
> Include the ovn-trace binary and it's man page in ovn-common package
>
> Fixes: 4acd1e87a8bf ("ovn-trace: New utility.")
> Fixes: f448e5a4bb1f ("rhel: Include ovn-trace in ovn-common package")
> Signed-off-by: Flavio Fernandes
T
On Fri, Oct 21, 2016 at 01:36:36PM -0700, Darrell Ball wrote:
> The first patch fixes arping from vtep-gw physical ports
> and the code change was done by Ramu Ramamurthy.
>
> The second patch adds additional comments regarding arp responders
> in ovn. This is intended to aid in understanding and
On Tue, Nov 01, 2016 at 04:19:59PM -0500, Flavio Fernandes wrote:
> Avoid leak due to missing ds_destroy in build_acl for non-stateful
> drop action.
>
> Found via inspection. I do not know that this fixes a common leak.
>
> Signed-off-by: Flavio Fernandes
Thanks! Applied to master and branch
Avoid leak due to missing ds_destroy in build_acl for non-stateful
drop action.
Found via inspection. I do not know that this fixes a common leak.
Signed-off-by: Flavio Fernandes
---
ovn/northd/ovn-northd.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/ovn/northd/ovn-northd.c b/ovn/north
On Tue, Oct 25, 2016 at 04:31:15PM -0400, Lance Richardson wrote:
> > From: "Lance Richardson"
> > To: dev@openvswitch.org
> > Sent: Tuesday, October 25, 2016 12:38:49 PM
> > Subject: [ovs-dev] [PATCH 2/2] ovn-southbound: implement read-only
> > connection support
> >
> > Add a connection table
On Tue, Oct 25, 2016 at 12:38:48PM -0400, Lance Richardson wrote:
> Adds a new "read_only" column for remote connections.
>
> Operations that would alter the state of the database are not
> permitted on connections for which the "read_only" column is set
> to "true".
>
> Signed-off-by: Lance Rich
On Mon, Oct 31, 2016 at 1:30 PM, Justin Pettit wrote:
>
>> On Oct 31, 2016, at 6:10 AM, Richard Theis wrote:
>>
>> > So, it turns out my fix does not introduce any new problems. I have
>> > just posted
>> > it, so consider if you want to wait to apply it before releasing.
>>
>> Just checking on t
On Tue, Nov 1, 2016 at 11:41 AM, Joe Stringer wrote:
> On 1 November 2016 at 11:35, Pravin B Shelar wrote:
>> The compat vlan code ignores vlan tag for inner packet
>> on egress path. Following patch fixes this by inserting the
>> tag for inner packet before tunnel encapsulation.
>>
>> Signed-off
On 1 November 2016 at 11:35, Pravin B Shelar wrote:
> The compat vlan code ignores vlan tag for inner packet
> on egress path. Following patch fixes this by inserting the
> tag for inner packet before tunnel encapsulation.
>
> Signed-off-by: Pravin B Shelar
Acked-by: Joe Stringer
__
The compat vlan code ignores vlan tag for inner packet
on egress path. Following patch fixes this by inserting the
tag for inner packet before tunnel encapsulation.
Signed-off-by: Pravin B Shelar
---
datapath/linux/compat/geneve.c | 33 +++--
1 file changed, 31 insert
Hi,
I measured the packet processing cost of OVS DPDK datapath for different
OpenFlow actions. I configured OVS to use a single pmd thread and measured the
packet throughput in a phy-to-phy setup. I used 10G interfaces bounded to DPDK
driver and overloaded the vSwitch with 64 byte packets thro
On Tue, Nov 1, 2016 at 11:06 AM, Joe Stringer wrote:
> On 1 November 2016 at 10:48, Pravin Shelar wrote:
>> On Tue, Nov 1, 2016 at 10:30 AM, Joe Stringer wrote:
>>> On 31 October 2016 at 22:00, Pravin B Shelar wrote:
The compat vlan code ignores vlan tag for inner packet
on egress pat
On 1 November 2016 at 10:48, Pravin Shelar wrote:
> On Tue, Nov 1, 2016 at 10:30 AM, Joe Stringer wrote:
>> On 31 October 2016 at 22:00, Pravin B Shelar wrote:
>>> The compat vlan code ignores vlan tag for inner packet
>>> on egress path. Following patch fixes this by inserting the
>>> tag for i
On Tue, Nov 1, 2016 at 10:30 AM, Joe Stringer wrote:
> On 31 October 2016 at 22:00, Pravin B Shelar wrote:
>> The compat vlan code ignores vlan tag for inner packet
>> on egress path. Following patch fixes this by inserting the
>> tag for inner packet before tunnel encapsulation.
>>
>> Signed-off
On 31 October 2016 at 22:00, Pravin B Shelar wrote:
> The compat vlan code ignores vlan tag for inner packet
> on egress path. Following patch fixes this by inserting the
> tag for inner packet before tunnel encapsulation.
>
> Signed-off-by: Pravin B Shelar
Is this a problem upstream and for oth
On Mon, Oct 31, 2016 at 05:23:25PM -0700, Joe Stringer wrote:
> On 31 October 2016 at 14:33, Ben Pfaff wrote:
> > On Mon, Oct 31, 2016 at 02:16:05PM -0700, Joe Stringer wrote:
> >> On 31 October 2016 at 13:23, Ben Pfaff wrote:
> >> > Some datapaths do not support the ct action, and others support
Add tc interface in order to send/recv data from/to the HW.
The kerenl side of tc will pass the tc messages to the driver and back.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/automake.mk | 2 +
lib/tc.c| 906
added operate implemenation using tc for flow offload,
supporting flow get, flow put, and flow del.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/dpif-hw-acc.c | 821 +-
lib/dpif-hw-acc.h | 10 +
2 files changed, 829 insertio
Added a new framework so user can specify which flows
to try and offload.
A new map was added to save each flow's policy.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/automake.mk | 2 ++
lib/dpif-hw-acc.c | 2 ++
lib/dpif-hw-acc.h | 1 -
lib/hw-offload-p
added support dump flows from tc.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/dpif-hw-acc.c | 248 ++
lib/dpif-hw-acc.h | 2 +
2 files changed, 232 insertions(+), 18 deletions(-)
diff --git a/lib/dpif-hw-acc.c b/lib/dpif-
added support to flush all offloaded flows from tc.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/dpif-hw-acc.c | 12
1 file changed, 12 insertions(+)
diff --git a/lib/dpif-hw-acc.c b/lib/dpif-hw-acc.c
index 0087e9c..98a99de 100644
--- a/lib/dpif-hw-acc.c
+++ b/li
Added infrastructure for a new provider that will be able
to send some flows to supporting HW for offloading.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/automake.mk | 2 +
lib/dpif-hw-acc.c | 444
lib/dpif-hw-acc.h
updating the port maps on dpif init and when
add/removing a port.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/dpif-hw-acc.c | 49 +
1 file changed, 45 insertions(+), 4 deletions(-)
diff --git a/lib/dpif-hw-acc.c b/lib/dpif-hw-a
converts a dumped tc flow back to dpif-flow,
for use in dumping/getting flows.
Signed-off-by: Paul Blakey
Signed-off-by: Shahar Klein
---
lib/dpif-hw-acc.c | 200 ++
1 file changed, 200 insertions(+)
diff --git a/lib/dpif-hw-acc.c b/lib/dpif-
Openvswitch currently configures the kerenel datapath via netlink over an
internal ovs protocol.
This patch series offers a new provider: dpif-netlink-tc that uses the tc
flower protocol
to offload ovs rules into HW data-path through netdevices that e.g represent
NIC e-switch ports.
The user
A flow in ovs can be identified by its ufid, and in tc by its
flow handle + priority.
We use the flow protocol number as the priority when offloading to tc.
So we save a map that maps from ovs ufid <-> tc flow handle + protocol.
Also added a map to map ovs in_port to/from netdevice to be used
when
On Tue, Nov 1, 2016 at 5:12 AM, Mauricio Vasquez B <
mauricio.vasq...@polito.it> wrote:
> Signed-off-by: Mauricio Vasquez B
> ---
> FAQ.rst | 106 +-
>
> INSTALL.DPDK.rst | 74 +--
> INSTALL.Debi
On Mon, Oct 31, 2016 at 10:53 PM, Justin Pettit wrote:
>
> > On Oct 31, 2016, at 12:22 PM, Russell Bryant wrote:
> >
> >
> >
> > On Mon, Oct 31, 2016 at 5:23 PM, Justin Pettit wrote:
> >
> >> > On Oct 29, 2016, at 9:19 AM, Russell Bryant wrote:
> >> >
> >> > +
> >> > +The following table ident
2016/10/28 19:17, Kavanagh, Mark B :
Currently, one packet is only copied to one segment
in function dpdk_do_tx_copy(), this could be an issue
when a jumboframe comes, especially for multipile segments.
Typos - 'jumboframe', 'multipile'
This patch doesn't apply cleanly - change 'mbufs' to 'p
2016/10/28 19:17, Kavanagh, Mark B :
Currently, one packet is only copied to one segment
in function dpdk_do_tx_copy(), this could be an issue
when a jumboframe comes, especially for multipile segments.
Typos - 'jumboframe', 'multipile'
This patch doesn't apply cleanly - change 'mbufs' to 'p
40 matches
Mail list logo
