On Tue, Oct 29, 2013 at 4:26 PM, Jesse Gross wrote:
> On Tue, Oct 29, 2013 at 2:10 PM, Pravin B Shelar wrote:
>> diff --git a/datapath/linux/compat/include/linux/netdevice.h
>> b/datapath/linux/compat/include/linux/netdevice.h
>> index c5c366b..14624bb 100644
>> --- a/datapath/linux/compat/inclu
Your message dated Tue, 29 Oct 2013 20:28:56 -0700
with message-id <20131030032856.gb10...@nicira.com>
and subject line Bug #691438: closing because of long-delayed explanation
has caused the Debian Bug report #691438,
regarding openvswitch packages do not work well together with upstream's kernel
From: Jesse Gross
Date: Tue, 29 Oct 2013 17:22:21 -0700
> From: Pravin B Shelar
>
> With mega flow implementation ovs flow can be shared between
> multiple CPUs which makes stats updates highly contended
> operation. Following patch allocates separate stats for each
> CPU to make stats update s
On Tue, Oct 29, 2013 at 04:39:52PM -0700, Jarno Rajahalme wrote:
> The naming of the classifier table has been a source of confusion,
> since each OpenFlow table is implemented as a classifier, which
> consists of multiple (sub)tables. This name change hopefully makes
> classifier related discussi
On Tue, 2013-10-29 at 18:25 -0700, Joe Perches wrote:
> On Tue, 2013-10-29 at 17:22 -0700, Jesse Gross wrote:
> > Over the time datapath.c and flow.c has became pretty large files.
> > Following patch restructures functionality of component into three
> > different components:
> []
> > net/openvsw
On Tue, 2013-10-29 at 17:22 -0700, Jesse Gross wrote:
> Over the time datapath.c and flow.c has became pretty large files.
> Following patch restructures functionality of component into three
> different components:
[]
> net/openvswitch/Makefile |2 +
> net/openvswitch/datapath.c |
On Tue, Oct 29, 2013 at 5:56 PM, Jesse Gross wrote:
> On Tue, Oct 29, 2013 at 3:57 PM, Alexei Starovoitov
> wrote:
>> On Tue, Oct 29, 2013 at 3:00 PM, Jesse Gross wrote:
>>> On Tue, Oct 29, 2013 at 11:19 AM, Alexei Starovoitov
>>> wrote:
On Tue, Oct 29, 2013 at 11:15 AM, Pravin Shelar wro
On Tue, Oct 29, 2013 at 3:57 PM, Alexei Starovoitov
wrote:
> On Tue, Oct 29, 2013 at 3:00 PM, Jesse Gross wrote:
>> On Tue, Oct 29, 2013 at 11:19 AM, Alexei Starovoitov
>> wrote:
>>> On Tue, Oct 29, 2013 at 11:15 AM, Pravin Shelar wrote:
On Tue, Oct 29, 2013 at 10:24 AM, Andy Zhou wrote:
From: Pravin B Shelar
ovs-flow rehash does not touch mega flow list. Following patch
moves it dp struct datapath. Avoid one extra indirection for
accessing mega-flow list head on every packet receive.
Signed-off-by: Pravin B Shelar
Signed-off-by: Jesse Gross
---
net/openvswitch/datapath.c
From: Jarno Rajahalme
Widen TCP flags handling from 7 bits (uint8_t) to 12 bits (uint16_t).
The kernel interface remains at 8 bits, which makes no functional
difference now, as none of the higher bits is currently of interest
to the userspace.
Signed-off-by: Jarno Rajahalme
Signed-off-by: Jesse
From: Pravin B Shelar
OVS already can handle all types of segmentation offloads that
are supported by the kernel.
Following patch specifically enables UDP and IPV6 segmentation
offloads.
Signed-off-by: Pravin B Shelar
Signed-off-by: Jesse Gross
---
net/openvswitch/vport-internal_dev.c | 2 +-
From: Jarno Rajahalme
tcp_flags=flags/mask
Bitwise match on TCP flags. The flags and mask are 16-bit num‐
bers written in decimal or in hexadecimal prefixed by 0x. Each
1-bit in mask requires that the corresponding bit in port must
match. Each 0-bit in m
From: Pravin B Shelar
Hides mega-flow implementation in flow_table.c rather than
datapath.c.
Signed-off-by: Pravin B Shelar
Signed-off-by: Jesse Gross
---
net/openvswitch/datapath.c | 27 +++--
net/openvswitch/flow_table.c | 138 +--
net/openvswi
From: Pravin B Shelar
With mega flow implementation ovs flow can be shared between
multiple CPUs which makes stats updates highly contended
operation. Following patch allocates separate stats for each
CPU to make stats update scalable.
Signed-off-by: Pravin B Shelar
Signed-off-by: Jesse Gross
From: Andy Zhou
Collect mega flow mask stats. ovs-dpctl show command can be used to
display them for debugging and performance tuning.
Signed-off-by: Andy Zhou
Signed-off-by: Jesse Gross
---
include/uapi/linux/openvswitch.h | 17 ++---
net/openvswitch/datapath.c | 38 +++
A set of updates for net-next/3.13. Major changes are:
* Restructure flow handling code to be more logically organized and
easier to read.
* Previously flow state was effectively per-CPU but this is no longer
true with the addition of wildcarded flows (megaflows). While good
for flow set
From: Pravin B Shelar
Rehashing in ovs-workqueue can cause ovs-mutex lock contentions
in case of heavy flow setups where both needs ovs-mutex. So by
moving rehashing to flow-setup we can eliminate contention.
This also simplify ovs locking and reduces dependence on
workqueue.
Signed-off-by: Pra
From: Wei Yongjun
Remove duplicated include.
Signed-off-by: Wei Yongjun
Signed-off-by: Jesse Gross
---
net/openvswitch/vport-vxlan.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index a481c03..b0da394 100644
--- a/net/openvsw
From: Wei Yongjun
Remove duplicated include.
Signed-off-by: Wei Yongjun
Signed-off-by: Jesse Gross
---
net/openvswitch/vport-gre.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index c99dea5..a3d6951 100644
--- a/net/openvswitch
The naming of the classifier table has been a source of confusion,
since each OpenFlow table is implemented as a classifier, which
consists of multiple (sub)tables. This name change hopefully makes
classifier related discussion a bit less confusing.
For consistency, relevant field names as well a
On Tue, Oct 29, 2013 at 2:10 PM, Pravin B Shelar wrote:
> diff --git a/datapath/linux/compat/include/linux/netdevice.h
> b/datapath/linux/compat/include/linux/netdevice.h
> index c5c366b..14624bb 100644
> --- a/datapath/linux/compat/include/linux/netdevice.h
> +++ b/datapath/linux/compat/include/
On Tue, Oct 29, 2013 at 3:00 PM, Jesse Gross wrote:
> On Tue, Oct 29, 2013 at 11:19 AM, Alexei Starovoitov
> wrote:
>> On Tue, Oct 29, 2013 at 11:15 AM, Pravin Shelar wrote:
>>> On Tue, Oct 29, 2013 at 10:24 AM, Andy Zhou wrote:
This is not a review, but it would be nice to add some code c
On Tue, Oct 29, 2013 at 10:12 AM, Pravin B Shelar wrote:
> diff --git a/datapath/datapath.h b/datapath/datapath.h
> index 879a830..5a89e0e 100644
> --- a/datapath/datapath.h
> +++ b/datapath/datapath.h
> @@ -53,29 +53,29 @@
> * up per packet.
> */
> struct dp_stats_percpu {
> + struct
On Tue, Oct 29, 2013 at 11:19 AM, Alexei Starovoitov
wrote:
> On Tue, Oct 29, 2013 at 11:15 AM, Pravin Shelar wrote:
>> On Tue, Oct 29, 2013 at 10:24 AM, Andy Zhou wrote:
>>> This is not a review, but it would be nice to add some code comments in
>>> proper data structure layout, so that the sam
From: Jesse Gross
Date: Mon, 28 Oct 2013 11:04:50 -0700
> One patch for net/3.12 fixing an issue where devices could be in an
> invalid state they are removed while still attached to OVS.
Pulled, thanks Jesse.
___
dev mailing list
dev@openvswitch.org
h
Move compat code to netdev_rx_handler_register() definition.
It also adds type safety for netdev-hook.
Signed-off-by: Pravin B Shelar
---
datapath/linux/compat/dev-openvswitch.c | 63 ++-
datapath/linux/compat/include/linux/netdevice.h | 37 +-
datapat
On Tue, Oct 29, 2013 at 04:52:50PM +0900, Simon Horman wrote:
> On Mon, Oct 28, 2013 at 11:47:32AM +0900, Simon Horman wrote:
> > On Mon, Oct 21, 2013 at 02:46:15PM -0700, Ben Pfaff wrote:
> > > On Tue, Oct 15, 2013 at 05:17:49PM +0900, Simon Horman wrote:
> > > > Allow translation of indirect and
On Tue, Oct 22, 2013 at 11:40:01AM +0300, Alexandru Copot wrote:
> This series adds the required functionality for notifying controllers
> with the OFPT_ROLE_STATUS message introduced in OpenFlow 1.4.
> Currently, this message is sent only when another controller asks
> that his role is changed to
Applied, thanks.
On Tue, Oct 29, 2013 at 01:34:46PM -0700, Bruce Davie wrote:
> This patch looks good, thanks.
>
> Bruce
>
> On Oct 29, 2013, at 1:02 PM, Ben Pfaff wrote:
>
> > A number of new key-value pairs have been added to the bfd and bfd_status
> > columns of the OVS schema since the VTEP
This patch looks good, thanks.
Bruce
On Oct 29, 2013, at 1:02 PM, Ben Pfaff wrote:
> A number of new key-value pairs have been added to the bfd and bfd_status
> columns of the OVS schema since the VTEP schema was created. To aid
> interoperability between OVS instances and VTEPs, this patch brin
On Mon, Oct 28, 2013 at 08:53:21AM -0700, Joe Stringer wrote:
> On 25 October 2013 22:10, Ben Pfaff wrote:
> OFPQT_NONE was removed from later standards because it was never defined
> > and it didn't make any sense to define it (why would you define a
> > property to say there are no properties?).
NVC is the correct term and, unlike NSC, it is defined in the glossary.
Signed-off-by: Ben Pfaff
CC: Bruce Davie
---
vtep/vtep.xml |4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/vtep/vtep.xml b/vtep/vtep.xml
index 9fd7495..6a7ccd6 100644
--- a/vtep/vtep.xml
+++ b/vte
On Thu, Oct 24, 2013 at 09:49:33AM -0700, Ben Pfaff wrote:
> This update improves the BFD documentation in a few ways:
>
>- Demand mode is now supported.
>
>- Wordsmithing, spelling, etc.
>
>- Attempt to better explain decay_min_rx, forwarding_if_rx, and
> cpath_down.
>
>-
This should have been marked as "v2", because I redid it based on the
new vswitch.xml wording. Bruce, will you look it over?
On Tue, Oct 29, 2013 at 01:02:23PM -0700, Ben Pfaff wrote:
> A number of new key-value pairs have been added to the bfd and bfd_status
> columns of the OVS schema since the
A number of new key-value pairs have been added to the bfd and bfd_status
columns of the OVS schema since the VTEP schema was created. To aid
interoperability between OVS instances and VTEPs, this patch brings
the VTEP schema into line with that of OVS.
CC: Bruce Davie
Signed-off-by: Ben Pfaff
-
On Thu, Oct 24, 2013 at 12:21:59PM -0700, Bruce Davie wrote:
> Looks mostly good (and a helpful improvement on the prior
> documentation). One small error:
Thanks, I fixed up the errors you reported and applied this to master.
> Would you like to update my vtep.xml patch with these improvements
On Tue, Oct 29, 2013 at 11:15 AM, Pravin Shelar wrote:
> On Tue, Oct 29, 2013 at 10:24 AM, Andy Zhou wrote:
>> This is not a review, but it would be nice to add some code comments in
>> proper data structure layout, so that the same logic can be followed in the
>> future.
>>
> ok, I will add gene
On Tue, Oct 29, 2013 at 10:24 AM, Andy Zhou wrote:
> This is not a review, but it would be nice to add some code comments in
> proper data structure layout, so that the same logic can be followed in the
> future.
>
ok, I will add general guideline in datapath.h as follows:
/*
* data structure me
On Tue, Oct 29, 2013 at 03:15:58PM -0200, Flavio Leitner wrote:
> On Tue, Oct 29, 2013 at 08:37:58AM -0700, Ben Pfaff wrote:
> > On Tue, Oct 29, 2013 at 10:51:02AM -0200, Flavio Leitner wrote:
> > > While updating the packages to 2.0.0 I found that the build fails on
> > > PPC.
> > >
> > > I am no
This is not a review, but it would be nice to add some code comments in
proper data structure layout, so that the same logic can be followed in the
future.
On Tue, Oct 29, 2013 at 10:12 AM, Pravin B Shelar wrote:
> Following patch rearranges various ovs structures which
> are accessed in datapat
On Tue, Oct 29, 2013 at 08:37:58AM -0700, Ben Pfaff wrote:
> On Tue, Oct 29, 2013 at 10:51:02AM -0200, Flavio Leitner wrote:
> > While updating the packages to 2.0.0 I found that the build fails on
> > PPC.
> >
> > I am not an expert on PPC arch, but I think it doesn't support atomic
> > operation
Following patch rearranges various ovs structures which
are accessed in datapath for optimal cacheline access.
Signed-off-by: Pravin B Shelar
---
datapath/datapath.h | 19 +--
datapath/flow.h | 13 ++---
datapath/flow_table.c |2 +-
datapath/vport.h |
On Mon, Oct 28, 2013 at 01:54:40PM -0700, Jarno Rajahalme wrote:
> tcp_flags=flags/mask
> Bitwise match on TCP flags. The flags and mask are 16-bit num???
> bers written in decimal or in hexadecimal prefixed by 0x. Each
> 1-bit in mask requires that the correspondi
Accepted:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Format: 1.8
Date: Tue, 29 Oct 2013 08:31:55 -0700
Source: openvswitch
Binary: openvswitch-datapath-source openvswitch-datapath-dkms
openvswitch-common openvswitch-switch openvswitch-ipsec openvswitch-pki
openvswitch-controller openvswi
On Oct 29, 2013, at 10:57 AM, Gurucharan Shetty wrote:
> The ovs-dpctl-top related changes were also needed for branch-2.0. I
> sent in a separate patch for that.
> http://openvswitch.org/pipermail/dev/2013-October/033362.html
>
Thanks, I just Acked that patch.
> On Thu, Oct 24, 2013 at 2:05 PM,
On Oct 29, 2013, at 10:56 AM, Gurucharan Shetty wrote:
> Signed-off-by: Gurucharan Shetty
> ---
> rhel/openvswitch-fedora.spec.in |2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/rhel/openvswitch-fedora.spec.in b/rhel/openvswitch-fedora.spec.in
> index 27a3b03..a818191 100644
> ---
The ovs-dpctl-top related changes were also needed for branch-2.0. I
sent in a separate patch for that.
http://openvswitch.org/pipermail/dev/2013-October/033362.html
On Thu, Oct 24, 2013 at 2:05 PM, Gurucharan Shetty wrote:
> This looks good to me.
> I verified that the Fedora rpm gets built fine
Signed-off-by: Gurucharan Shetty
---
rhel/openvswitch-fedora.spec.in |2 ++
1 file changed, 2 insertions(+)
diff --git a/rhel/openvswitch-fedora.spec.in b/rhel/openvswitch-fedora.spec.in
index 27a3b03..a818191 100644
--- a/rhel/openvswitch-fedora.spec.in
+++ b/rhel/openvswitch-fedora.spec.in
openvswitch_1.9.3+git20131029-1_i386.changes uploaded successfully to localhost
along with the files:
openvswitch_1.9.3+git20131029-1.dsc
openvswitch_1.9.3+git20131029.orig.tar.xz
openvswitch_1.9.3+git20131029-1.debian.tar.gz
openvswitch-common_1.9.3+git20131029-1_i386.deb
openvswitch-swi
On Tue, Oct 29, 2013 at 10:51:02AM -0200, Flavio Leitner wrote:
> While updating the packages to 2.0.0 I found that the build fails on
> PPC.
>
> I am not an expert on PPC arch, but I think it doesn't support atomic
> operations of 8 bytes (64bit) on 32bit system, then there is no GCC
> built-in[1
Hi folks,
While updating the packages to 2.0.0 I found that the build fails on
PPC.
I am not an expert on PPC arch, but I think it doesn't support atomic
operations of 8 bytes (64bit) on 32bit system, then there is no GCC
built-in[1] for those cases which breaks the build.
[1] http://gcc.gnu.or
On Mon, Oct 28, 2013 at 11:47:32AM +0900, Simon Horman wrote:
> On Mon, Oct 21, 2013 at 02:46:15PM -0700, Ben Pfaff wrote:
> > On Tue, Oct 15, 2013 at 05:17:49PM +0900, Simon Horman wrote:
> > > Allow translation of indirect and all groups. Also allow insertion of
> > > indirect and all groups by
52 matches
Mail list logo
