t would be good to zero
out this newly allocated memory to avoid any possible subtle problems.
But otherwise I am happy with this:
Acked-by: Jesse Gross
I think that's everything on this series at this point! Thanks for all
of the revisions. (I don't feel the need to take another l
;
> Reported-by: Justin Pettit
> Reported-by: Joe Stringer
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Fri, Feb 19, 2016 at 4:03 PM, Pravin B Shelar wrote:
> Currently OVS out of tree datapath supports a large number of kernel
> versions. From 2.6.32 to 4.3 and various distribution-specific
> kernels. But at this point major features are only available on more
> recent kernels. For example, sta
On Tue, Feb 23, 2016 at 9:01 PM, Pravin B Shelar wrote:
> diff --git a/FAQ.md b/FAQ.md
> index 8bd7ab9..8e0a775 100644
> --- a/FAQ.md
> +++ b/FAQ.md
> @@ -157,6 +157,7 @@ A: The following table lists the Linux kernel versions
> against which the
> |2.3.x | 2.6.32 to 3.14
> |2.4.x
On Tue, Feb 23, 2016 at 9:01 PM, Pravin B Shelar wrote:
> This macro is not required as we drop support for unsupported
> kernel versions.
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswi
On Tue, Feb 16, 2016 at 2:15 PM, Jiri Benc wrote:
> Sorry for the late answer, was busy with a conference and internal
> meetings in the past two weeks.
>
> On Tue, 2 Feb 2016 17:15:15 -0800, Jesse Gross wrote:
>> I think this sounds like a good idea if we can find a way to do i
On Thu, Feb 25, 2016 at 10:13 PM, Jiri Benc wrote:
> On Thu, 25 Feb 2016 17:32:28 -0800, Jesse Gross wrote:
>> The thing that bothers me about this is that it's not really a binary
>> split between Ethernet and IP. L2 "obviously" means Ethernet (although
>>
On Sun, Feb 28, 2016 at 10:29 PM, Ajmer Singh wrote:
> Hi,
>
> We are working on open Vswitch 2.4 and the requirement is to add GTP tunnel
> headers in flow table so that onos controller can add flows for GTP packets
> and the switch captures GTP packets as well. What we have identified so far:
>
On Tue, Mar 8, 2016 at 9:24 PM, Ajmer Singh wrote:
> I have now question related to mapping of ofp_header->type (OFPT_) with
> OFPRAW_contants
>
> struct ofp_header {
> uint8_t version;/* An OpenFlow version number, e.g. OFP10_VERSION.
> */
> uint8_t type; /* One of the OFPT_ con
On Wed, Mar 9, 2016 at 4:40 PM, Pravin B Shelar wrote:
> From: Pravin B Shelar
>
> There is check to disable IPv6 tunneling. Following patch
> removes it and reintroduces the tunneling automake tests.
>
> This reverts commit 250bd94d1e500a89c76cac944e660bd9c07ac364.
>
> Signed-off-by: Pravin B Sh
ce_extended])
I don't think either of these symbols are referenced any more.
Otherwise this looks good - we can continue to remove dead code in the
compat directory as time goes on.
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
build/openvswitch/ovs/datapath'
> make: *** [distdir] Error 1
> cat: */_build/tests/testsuite.log: No such file or directory
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Sun, Mar 13, 2016 at 8:39 PM, William Tu wrote:
> Hi Darrell,
>
> Thanks, however, it still doesn't work for me. On linux 4.3, modules that
> depends on openvswitch.ko are
> vport-gre
> vport-vxlan
> vport-geneve
> I've made sure they all unloaded, but my openvswitch.ko still shows "used
> by 4
On Mon, Mar 14, 2016 at 1:55 PM, William Tu wrote:
> Hi Jesse,
>
> Thanks! It works... although I don't quite understand why.
>
> [root@vm-dev ovs]# ovs-appctl -t ovs-vswitchd exit
> [root@vm-dev ovs]# ovs-appctl -t ovsdb-server exit
> [root@vm-dev ovs]# lsmod | grep open
> openvswitch 1
t; encapsulation occurs and the contention on the inner_protocol field of the
> skb no longer occurs.
>
> Thus it is now safe to output MPLS to tunnel vports.
>
> Signed-off-by: Simon Horman
Reviewed-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Tue, Mar 15, 2016 at 9:57 AM, Pravin B Shelar wrote:
> diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
> index f7b7b9c..98377b0 100644
> --- a/vswitchd/vswitch.xml
> +++ b/vswitchd/vswitch.xml
> @@ -1951,7 +1951,7 @@
>
>
>
> -An IPv4 address (not a DNS
On Thu, Mar 10, 2016 at 7:43 PM, Alexandru Ardelean
wrote:
> A bit cleaner than my previous patch.
> http://patchwork.ozlabs.org/patch/595969/
>
> Though I couldn't figure out a clean solution for ip6_local_out(),
> genl_notify(), and vport-vxlan
>
> Signed-off-by: Alexandru Ardelean
The best
On Fri, Mar 18, 2016 at 6:34 AM, Arnd Bergmann wrote:
> This means it's still too large really, we just don't warn about it any more,
> and will get the warning again once another member is added. My patch is a
> band-aid at best, but more work is needed here. One problem is that
> ovs_flow_cmd_ne
On Wed, Mar 16, 2016 at 5:16 PM, Ben Pfaff wrote:
> On Wed, Mar 16, 2016 at 05:06:16PM -0700, Jesse Gross wrote:
>> On Wed, Mar 16, 2016 at 4:45 PM, Ben Pfaff wrote:
>> > OVS 1.7 was released in July 2012, so by the time current OVS is released,
>> > it will be almo
On Thu, Mar 17, 2016 at 9:24 AM, Samuel Gauthier
wrote:
> 2016-03-17 0:23 GMT+01:00 Jesse Gross :
>> On Wed, Mar 16, 2016 at 8:07 AM, Samuel Gauthier
>> wrote:
>>> This patchset adds a netlink api to refresh an existing flow in
>>> openvswitch.
>>>
&g
On Wed, Mar 16, 2016 at 4:45 PM, Ben Pfaff wrote:
> OVS 1.7 was released in July 2012, so by the time current OVS is released,
> it will be almost four years old. I think that this is long enough to
> remove special upgrade code.
>
> Signed-off-by: Ben Pfaff
Acked-by: Jesse Gros
On Thu, Mar 17, 2016 at 3:43 PM, Chandran, Sugesh
wrote:
> Hi,
>
> This patch proposes an approach that uses Flow director feature on the Intel
> Fortville NICs to boost the VxLAN tunneling performance. In our testing we
> verified that the VxLAN performance is almost doubled with this patch.
>
On Wed, Mar 16, 2016 at 8:07 AM, Samuel Gauthier
wrote:
> This patchset adds a netlink api to refresh an existing flow in
> openvswitch.
>
> When a packet is sent in the openvswitch kernel datapath and no
> flow is found, the packet is sent to the ovs-vswitchd daemon,
> which will process the pack
].*)
> -action "Saving ofport values" ovs_save save-ofports \
> -"${script_ofports}"
I think we can now remove the script_ofports initialization from
init_restore_scripts now that it is no longer used.
Otherwise it looks good though.
Acked-by: Jes
rsion of the function from a newer
kernel, this simply ignores the version that Ubuntu is now making available
and continues to use the OVS version, similar to what it was doing before.
Reported-by: Zoltán Balogh
Reported-by: Aaron Rosen
Reported-by: Russell Bryant
Signed-off-by: Jes
On Mon, Mar 21, 2016 at 12:49 PM, Russell Bryant wrote:
> On Mon, Mar 21, 2016 at 12:43 PM, Jesse Gross wrote:
>>
>> Ubuntu 3.13.0-83-generic has backported a patch that adds an intermediate
>> version of the v6ops->fragment function that doesn't seem to ever been
&
On Mon, Mar 21, 2016 at 1:07 PM, Russell Bryant wrote:
>
>
> On Mon, Mar 21, 2016 at 12:59 PM, Jesse Gross wrote:
>>
>> On Mon, Mar 21, 2016 at 12:49 PM, Russell Bryant wrote:
>> > On Mon, Mar 21, 2016 at 12:43 PM, Jesse Gross wrote:
>> >>
>> &g
On Thu, Mar 24, 2016 at 7:30 AM, Robert Wojciechowicz
wrote:
> This patch configures RSS hash filter in DPDK in order to include
> source and destination MAC addresses into RSS hash calculation.
> This configuration considerably improves performance for flows
> with overlapping IP address spaces a
On Fri, Mar 18, 2016 at 8:50 AM, Chandran, Sugesh
wrote:
> Hi Jesse,
> Please find my answers inline.
>
> Regards
> _Sugesh
>
>
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Thursday, March 17, 2016 11:50
On Fri, Mar 25, 2016 at 7:45 AM, Wojciechowicz, RobertX
wrote:
> Hi Jesse,
>
> please find my answers inline.
>
>> -Original Message-----
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Thursday, March 24, 2016 11:20 PM
>> To: Wojciechowicz, Rob
On Tue, Mar 29, 2016 at 12:43 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Friday, March 25, 2016 12:38 AM
>> To: Chandran, Sugesh
>> Cc: dev@openvswitch.org
>> Subject: Re: [ovs-dev] [R
On Wed, Mar 30, 2016 at 10:27 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Wednesday, March 30, 2016 1:44 AM
>> To: Chandran, Sugesh
>> Cc: dev@openvswitch.org
>> Subject: Re: [ovs-dev] [R
On Thu, Mar 31, 2016 at 2:30 PM, Pravin B Shelar wrote:
> STT implementation we saw performance improvements with linearizing
> skb for SLUB case. So following patch skips zero copy operation
> for such a case.
>
> Tested-By: Vasmi Abidi
> Signed-off-by: Pravin B Shelar
Can you add some perfor
On Fri, Apr 1, 2016 at 4:58 PM, pravin shelar wrote:
> On Thu, Mar 31, 2016 at 9:06 PM, Jesse Gross wrote:
>> On Thu, Mar 31, 2016 at 2:30 PM, Pravin B Shelar wrote:
>>> diff --git a/datapath/linux/compat/stt.c b/datapath/linux/compat/stt.c
>>> index eb397e8..ae33d5
On Mon, Apr 4, 2016 at 7:57 PM, pravin shelar wrote:
> On Mon, Apr 4, 2016 at 1:56 PM, Jesse Gross wrote:
>> On Fri, Apr 1, 2016 at 4:58 PM, pravin shelar wrote:
>>> On Thu, Mar 31, 2016 at 9:06 PM, Jesse Gross wrote:
>>>> On Thu, Mar 31, 2016 at 2:30 PM, Prav
On Mon, Apr 11, 2016 at 2:52 AM, Sugesh Chandran
wrote:
> Optimizing VxLAN tunneling performance in userspace datapath by offloading
> the rx checksum validation on tunnel packets to the NIC when it is supported.
>
> Signed-off-by: Sugesh Chandran
Thanks for working on this. I think there is a l
On Wed, Apr 13, 2016 at 5:42 AM, Wojciechowicz, RobertX
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Friday, March 25, 2016 7:57 PM
>> To: Wojciechowicz, RobertX
>> Cc: ovs dev
>> Subject: Re: [ovs-dev] [PAT
On Wed, Aug 10, 2016 at 10:34 AM, Pravin B Shelar wrote:
> Remove mutual exclusion between udp-gro registration and geneve receive port
> registration.
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev mailing list
dev@ope
On Wed, Aug 10, 2016 at 10:34 AM, Pravin B Shelar wrote:
> Same as earlier patch this fixes vxlan recieve offload implementation.
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvs
On Thu, Aug 11, 2016 at 2:12 PM, Pravin B Shelar wrote:
> When using compat GSO there is no need to turn on skb
> encapsulation bit since OVS does not use any tunnel GSO
> functionality from the networking stack.
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
And,
of incremental processing
which the first two patches fix.
I'm targetting this for OVS 2.6 since the bulk of the changes are bug fixes
and the benefits from the UDP checksums are significant.
Jesse Gross (3):
ovn-controller: Fix memory leak when updating tunnels.
ovn-controller: Make
When a tunnel possibly needs to be updated, we are currently allocating
a new name for it. This is not necessary and in fact nothing uses the
name, which then results in the memory being leaked.
Fixes: 1d45d5a9 ("ovn-controller: Change encaps_run to work incrementally.")
Signed-off
work incrementally.")
Signed-off-by: Jesse Gross
---
ovn/controller/encaps.c | 471 +---
ovn/controller/ovn-controller.c | 1 +
2 files changed, 248 insertions(+), 224 deletions(-)
diff --git a/ovn/controller/encaps.c b/ovn/controller/encaps.c
ind
ff-by: Jesse Gross
---
ovn/controller-vtep/gateway.c | 9 +
ovn/controller/chassis.c | 8
ovn/controller/encaps.c | 12 +++-
ovn/ovn-sb.xml| 10 --
ovn/utilities/ovn-sbctl.c | 2 ++
tests/ovn-controller-vtep.at | 1 +
tests/ovn-sbc
ly thus need no modification.
>
> Thanks to Ben for some pointers from the crash dumps!
>
> Cc: Benjamin Poirier
> Cc: Paolo Abeni
> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1361414
> Signed-off-by: Ian Wienand
> Signed-off-by: David S. Miller
On Fri, Aug 12, 2016 at 10:49 AM, Pravin B Shelar wrote:
> Upstream commit:
> commit 4b5b9ba553f9aa5f484ab972fc9b58061885ceca
> Author: Martynas Pumputis
> Date: Tue Aug 9 16:24:50 2016 +0100
>
> openvswitch: do not ignore netdev errors when creating tunnel vports
>
> The cr
On Fri, Aug 12, 2016 at 12:57 PM, Ben Pfaff wrote:
> On Thu, Aug 11, 2016 at 05:20:33PM -0700, Jesse Gross wrote:
>> Originally, processing of encapsulations simply iterated over all tables on
>> every wakeup and would replace anything that changed. This is somewhat
>> ineffi
On Thu, Aug 11, 2016 at 7:10 PM, Ryan Moats wrote:
> "dev" wrote on 08/11/2016 07:20:34 PM:
>
>> From: Jesse Gross
>> To: dev@openvswitch.org
>> Date: 08/11/2016 07:22 PM
>> Subject: [ovs-dev] [PATCH rebase 3/3] ovn-controller: Use UDP
>> checksums
On Fri, Aug 12, 2016 at 1:06 PM, Ben Pfaff wrote:
> On Thu, Aug 11, 2016 at 05:20:34PM -0700, Jesse Gross wrote:
>> Currently metadata transmitted by OVN over Geneve tunnels is
>> unprotected by any checksum other than the one provided by the link
>> layer - this includes
XLATE_REPORT_ERROR is a macro that takes struct xlate_ctx as an
argument but also implicitly uses 'ctx' from the local function
scope. This is works with current uses but it really should be
using the argument.
Signed-off-by: Jesse Gross
---
ofproto/ofproto-dpif-xlate.c | 2 +-
1 fi
On Mon, Aug 15, 2016 at 9:22 AM, Ben Pfaff wrote:
> On Mon, Aug 15, 2016 at 08:21:19AM -0700, Jesse Gross wrote:
>> XLATE_REPORT_ERROR is a macro that takes struct xlate_ctx as an
>> argument but also implicitly uses 'ctx' from the local function
>> scope. This is
e binding fails (e.g. due to the
> port being in use), the error is currently ignored giving the
> appearance that the tunnel vport creation completed successfully.
>
> Signed-off-by: Martynas Pumputis
> Acked-by: Pravin B Shelar
> Signed-off-by: D
On Fri, Aug 12, 2016 at 1:01 AM, Jan Scheurich
wrote:
> The only clean way to avoid that now would be to maintain the monolithic
> push/pop_nsh semantic of the Yi Yang patch and always push/pop NSH header and
> outer MAC header together. Together with Simon's patch we could still achieve
> NSH
On Mon, Aug 8, 2016 at 3:03 AM, Sugesh Chandran
wrote:
> To enable checksum offloading at rx side while adding a port, add the
> 'rx-checksum-offload' option to the 'ovs-vsctl add-port' command-line as
> below,
>
> 'ovs-vsctl add-port br0 dpdk0 -- \
> set Interface dpdk0 type=dpdk options:rx-chec
nclude the
critical bit to properly mark the intention. Obviously, this will
cause interoperability issues with any existing deployments but
it should be fine while OVN is still labeled as experimental.
Signed-off-by: Jesse Gross
---
ovn/controller/physical.h | 2 +-
ovn/ovn-architecture.7.xml | 2 +
On Mon, Aug 15, 2016 at 2:11 PM, Pravin B Shelar wrote:
> diff --git a/datapath/linux/compat/gso.c b/datapath/linux/compat/gso.c
> index 89df07f..f973fb4 100644
> --- a/datapath/linux/compat/gso.c
> +++ b/datapath/linux/compat/gso.c
> @@ -236,9 +236,6 @@ static int output_ip(struct sk_buff *skb)
>
;csum_help' argument to iptunnel_handle_offloads
>
> All users now pass false, so we can remove it, and remove the code that
> was conditional upon it.
>
> Signed-off-by: Edward Cree
> Signed-off-by: David S. Miller
>
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse G
On Mon, Aug 15, 2016 at 2:11 PM, Pravin B Shelar wrote:
> With use of LCO support we can finally enable SG and CSUM
> features for GSO backport.
>
> Signed-off-by: Pravin B Shelar
I don't know if this is safe. The kernels where this function is
called are the ones without ndo_features_check, so
On Tue, Aug 16, 2016 at 2:04 PM, Russell Bryant wrote:
>
> On Tue, Aug 16, 2016 at 4:58 PM, Jesse Gross wrote:
>>
>> Currently the Geneve option type that OVN uses is 0, which in
>> Geneve marks this as non-critical. Non-critical means that if a
>> receiver does no
On Wed, Aug 17, 2016 at 10:23 AM, Pravin B Shelar wrote:
> diff --git a/datapath/linux/compat/gso.c b/datapath/linux/compat/gso.c
> index 89df07f..48a56b9 100644
> --- a/datapath/linux/compat/gso.c
> +++ b/datapath/linux/compat/gso.c
> @@ -236,12 +236,12 @@ static int output_ip(struct sk_buff *skb
On Tue, Aug 16, 2016 at 3:06 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Monday, August 15, 2016 6:44 PM
>> To: Chandran, Sugesh
>> Cc: ovs dev
>> Subject: Re: [PATCH RFC] netdev-dpd
These tests dump the flows currently in the datapath but they aren't
the first to run and might have existing flows left over. We don't
really care if there are others flows present so filter on the ones
we want to avoid being affected by the timing of flow eviction.
Signed-off-by: J
On Wed, Aug 17, 2016 at 10:17 PM, pravin shelar wrote:
> On Wed, Aug 17, 2016 at 5:26 PM, Jesse Gross wrote:
>> On Wed, Aug 17, 2016 at 10:23 AM, Pravin B Shelar wrote:
>>> diff --git a/datapath/linux/compat/gso.c b/datapath/linux/compat/gso.c
>>> index 89df07
On Thu, Aug 18, 2016 at 4:36 PM, pravin shelar wrote:
> On Thu, Aug 18, 2016 at 12:26 PM, Jesse Gross wrote:
>> These tests dump the flows currently in the datapath but they aren't
>> the first to run and might have existing flows left over. We don't
>> really
Some tunnel flags are purely internal implementation details (primarily
FLOW_TNL_F_UDPIF). These shouldn't be output when we format tunnel
flows, so this masks them out.
Signed-off-by: Jesse Gross
---
lib/match.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
On Thu, Aug 18, 2016 at 9:23 PM, santhu vaddepally
wrote:
> Hi,
>
> Please , Can any one tell me whether openvSwitch-2.5.0 supports VXLAN
> over IPSEC. I didn't find any stuff regarding support of VXLAN over IPSEC
> in README or other. Is this feasible with the updated package ?
No, it's not
On Fri, Aug 19, 2016 at 8:54 AM, Ben Pfaff wrote:
> On Thu, Aug 18, 2016 at 05:25:25PM -0700, Jesse Gross wrote:
>> Some tunnel flags are purely internal implementation details (primarily
>> FLOW_TNL_F_UDPIF). These shouldn't be output when we format tunnel
>> flo
On Fri, Aug 19, 2016 at 3:40 AM, Sugesh Chandran
wrote:
> diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
> index e5f2cdd..113e6d8 100644
> --- a/lib/netdev-dpdk.c
> +++ b/lib/netdev-dpdk.c
> @@ -1090,6 +1127,15 @@ netdev_dpdk_set_config(struct netdev *netdev, const
> struct smap *args)
>
>
On Mon, Aug 22, 2016 at 6:38 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Saturday, August 20, 2016 2:07 AM
>> To: Chandran, Sugesh
>> Cc: ovs dev
>> Subject: Re: [RFC PATCHv2] netdev
On Mon, Aug 22, 2016 at 6:40 AM, Sugesh Chandran
wrote:
> diff --git a/lib/netdev-native-tnl.c b/lib/netdev-native-tnl.c
> index ce2582f..78ce0c9 100644
> --- a/lib/netdev-native-tnl.c
> +++ b/lib/netdev-native-tnl.c
> @@ -85,11 +85,17 @@ netdev_tnl_ip_extract_tnl_md(struct dp_packet *packet,
> s
--
> 5 files changed, 17 insertions(+), 4 deletions(-)
Acked-by: Jesse Gross
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
in the original packet
format in more cases. This helps when copies need to be made as the amount
of data touched is only what is present in the packet rather than the
maximum amount of metadata supported.
Co-authored-by: Madhu Challa
Signed-off-by: Madhu Challa
Signed-off-by: Jesse Gross
On Tue, Aug 23, 2016 at 9:12 AM, Jan Scheurich
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Monday, 15 August, 2016 19:12
>>
>> On Fri, Aug 12, 2016 at 1:01 AM, Jan Scheurich
>> wrote:
>> > The only cle
On Tue, Aug 23, 2016 at 2:57 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Monday, August 22, 2016 7:50 PM
>> To: Chandran, Sugesh
>> Cc: ovs dev
>> Subject: Re: [RFC PATCHv3] netdev
On Wed, Aug 24, 2016 at 7:54 AM, Sugesh Chandran
wrote:
> diff --git a/lib/netdev-native-tnl.c b/lib/netdev-native-tnl.c
> index ce2582f..31a12d6 100644
> --- a/lib/netdev-native-tnl.c
> +++ b/lib/netdev-native-tnl.c
> @@ -179,20 +181,26 @@ udp_extract_tnl_md(struct dp_packet *packet, struct
> fl
On Thu, Aug 25, 2016 at 2:43 AM, Sugesh Chandran
wrote:
> diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
> index 6d334db..46c4045 100644
> --- a/lib/netdev-dpdk.c
> +++ b/lib/netdev-dpdk.c
> static void
> +dpdk_eth_checksum_offload_configure(struct netdev_dpdk *dev)
> +OVS_REQUIRES(dev->m
On Fri, Aug 26, 2016 at 2:39 AM, Chandran, Sugesh
wrote:
>> -Original Message-
>> From: Jesse Gross [mailto:je...@kernel.org]
>> Sent: Thursday, August 25, 2016 10:09 PM
>> To: Chandran, Sugesh
>> Cc: ovs dev
>> Subject: Re: [RFC PATCHv5] netdev
Rx checksum offloading still offers 8-9% of improvement on VxLAN tunneling
> decapsulation even though the SSE vector Rx function is disabled in DPDK poll
> mode driver.
>
> Signed-off-by: Sugesh Chandran
Thanks for all of the revisions! This one looks good to me. I'll look
forwar
returned field is simply zeroed. This
makes sorting based on tunnel metadata non-deterministic.
We have the tunnel allocation stored in match metadata with each
flow, so we can simply extract the data from there rather than
trying to build and populate a global mapping table.
Signed-off-by: Jesse Gross
lows.
Signed-off-by: Jesse Gross
---
tests/ovs-ofctl.at| 28 +++
utilities/ovs-ofctl.c | 209 +-
2 files changed, 218 insertions(+), 19 deletions(-)
diff --git a/tests/ovs-ofctl.at b/tests/ovs-ofctl.at
index 00db247..d966fc2 100644
--- a/test
king to work
>properly with tunnels)
> 2. ca3574d5 (IPsec: refactor out some code in
>OVS_MONITOR_IPSEC_START macro)
>
> Signed-off-by: Ansis Atteka
> Reported-by: Steffen Birkeland
Acked-by: Jesse Gross
___
dev mailing list
de
On Sun, Aug 28, 2016 at 3:51 PM, Ryan Moats wrote:
> diff --git a/ovn/controller/encaps.c b/ovn/controller/encaps.c
> index d99ba05..87f 100644
> --- a/ovn/controller/encaps.c
> +++ b/ovn/controller/encaps.c
> +SBREC_CHASSIS_FOR_EACH (chassis_rec, ctx->ovnsb_idl) {
> +for (int i =
. Otherwise, the instance
of OVS receiving the new flows won't know the meaning of these
fields and will ignore them.
Signed-off-by: Jesse Gross
---
utilities/ovs-save | 6 ++
1 file changed, 6 insertions(+)
diff --git a/utilities/ovs-save b/utilities/ovs-save
index d4d3c35..4ae8fde 100755
On Tue, Aug 30, 2016 at 3:22 PM, Ben Pfaff wrote:
> On Mon, Aug 29, 2016 at 11:58:14AM -0700, Jesse Gross wrote:
>> When flows are read by ovs-ofctl (either from a switch or a file),
>> tunnel metadata space is dynamically allocated since there isn't a
>> preset table.
On Tue, Aug 30, 2016 at 3:34 PM, Ben Pfaff wrote:
> On Tue, Aug 30, 2016 at 02:16:36PM -0700, Jesse Gross wrote:
>> Scripts that integrate OVS with a distribution often save and
>> restore flows across distruptive events, such as an upgrade. The
>> ovs-save utility generat
On Wed, Aug 31, 2016 at 2:30 AM, Yang, Zhiyong wrote:
> Hi, all:
>
> Physical NIC has a set of hardware counters, such as
> u64 prc64;
> u64 prc127;
> u64 prc255; etc.
> DPDK counts the prc64 in two ways. Physical NIC counts prc64 with CRC by
> hardware. Virtio computes the counter like prc64 with
On Tue, Aug 30, 2016 at 6:47 PM, Daniele Di Proietto
wrote:
> When translating a set action we also unwildcard the field in question.
> This is done to correctly translate set actions with the value identical
> to the ingress flow, like in the following example:
>
> flow table:
>
> tcp,actions=set
On Thu, Sep 1, 2016 at 10:17 AM, Daniele Di Proietto
wrote:
> Let me try to sum up the problem further
>
> 1) Behavior on master, before commit 47bf118665a3("ofproto: Always set MTU
> for new internal ports."):
>
> a) When an internal interface is added, or its MTU has changed we only
> chan
On Tue, Aug 30, 2016 at 1:17 PM, Ben Pfaff wrote:
> On Tue, Aug 23, 2016 at 02:28:27PM -0700, Jesse Gross wrote:
>> When using tunnel TLVs (at the moment, this means Geneve options), a
>> controller must first map the class and type onto an appropriate OXM
>> field so that
in the original packet
format in more cases. This helps when copies need to be made as the amount
of data touched is only what is present in the packet rather than the
maximum amount of metadata supported.
Co-authored-by: Madhu Challa
Signed-off-by: Madhu Challa
Signed-off-by: Jesse Gross
erved. Therefore it appears to be safe to bring this in
> line with upstream without any other workarounds.
>
> Reported-by: Jesse Gross
> Signed-off-by: Joe Stringer
If you are confident that it doesn't cause problems on older kernels,
the change looks obviously correct to me
On Wed, Sep 7, 2016 at 5:18 PM, Joe Stringer wrote:
> On 1 September 2016 at 18:08, Jesse Gross wrote:
>> On Thu, Sep 1, 2016 at 5:01 PM, Joe Stringer wrote:
>>> The upstream code uses NF_INET_PRE_ROUTING hook for the nf_conntrack_in()
>>> call, which does deeper (eg
On Fri, Sep 9, 2016 at 8:55 AM, Ben Pfaff wrote:
> Our previously announced plan for OVS 2.6 is to release on Sept. 15, in
> less than a week. In the OVN meeting in IRC yesterday, we already
> discussed a few OVN bugs that should be fixed before the release. All
> of them seem like they can be f
On Fri, Sep 9, 2016 at 2:37 PM, Joe Stringer wrote:
> On 8 September 2016 at 08:49, Jesse Gross wrote:
>> On Wed, Sep 7, 2016 at 5:18 PM, Joe Stringer wrote:
>>> On 1 September 2016 at 18:08, Jesse Gross wrote:
>>>> On Thu, Sep 1, 2016 at 5:01 PM, Joe Stringer
The script accidentally hardcoded the bridge name as 'br-int',
a leftover from testing.
Reported-by: Huanle Han
Signed-off-by: Jesse Gross
---
utilities/ovs-save | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/utilities/ovs-save b/utilities/ovs-save
index 4ae8fd
On Mon, Sep 12, 2016 at 10:22 AM, Ramu Ramamurthy
wrote:
> Hi,
>
> I dont see a /proc filesystem based interface to help debug the
> openvswitch kernel module. Some of the knobs that may be useful are:
> a) debug knobs for stats (for those stats are not already reported),
> b) control knobs like:
On Mon, Sep 12, 2016 at 2:48 PM, Pravin B Shelar wrote:
> This allows openvswitch and geneve module co-exist kernel on newer
> kernels.
>
> Reported-by: Joe Stringer
> Signed-off-by: Pravin B Shelar
Acked-by: Jesse Gross
___
dev m
On Tue, Sep 13, 2016 at 1:18 PM, Alin Serdean
wrote:
> On the Windows side we still have to integrate multiple internal/external
> ports. As it was discussed before, I was wondering if they could be
> integrated in 2.6.
I think we're really past the time where it makes sense to be adding
new fe
in the original packet
format in more cases. This helps when copies need to be made as the amount
of data touched is only what is present in the packet rather than the
maximum amount of metadata supported.
Co-authored-by: Madhu Challa
Signed-off-by: Madhu Challa
Signed-off-by: Jesse Gross
On Thu, Sep 15, 2016 at 10:43 AM, Ben Pfaff wrote:
> On Sun, Sep 11, 2016 at 06:26:23PM -0700, Jesse Gross wrote:
>> The script accidentally hardcoded the bridge name as 'br-int',
>> a leftover from testing.
>>
>> Reported-by: Huanle Han
>> Signed-o
301 - 400 of 3414 matches
Mail list logo
