On 12/12/22 7:41 AM, Dumitru Ceara wrote:
> On 12/5/22 17:07, Dumitru Ceara wrote:
>> On 9/30/22 12:43, Dumitru Ceara wrote:
>>> On 9/20/22 22:18, Mark Michelson wrote:
Thanks Ales,
Acked-by: Mark Michelson
>>>
>>> I applied this to the main branch and backported it to all
On Thu, Dec 15, 2022 at 4:38 PM Han Zhou wrote:
>
> On Mon, Dec 12, 2022 at 1:28 AM venu iyer wrote:
> >
> > Currently, even stateless flows are subject to connection tracking when
> there are
> > LB rules (for DNAT). However, if a flow needs to be subjected to LB, then
> it shouldn't
> > be
On Fri, Dec 16, 2022 at 4:52 PM Simon Horman wrote:
>
> From: Peng Zhang
>
> This commit adds support for OVS-DPDK with -DALLOW_EXPERIMENTAL_API.
>
> Tunnel offloads and Meter offloads are experimental APIs in DPDK. To
> enable these features, compile need add -DALLOW_EXPERIMENTAL_API. So
> in
On 09/12/2022 15:13, David Marchand wrote:
Hi Kevin,
Here are some comments on the stats side:
On Tue, Nov 29, 2022 at 3:01 PM Kevin Traynor wrote:
@@ -6964,5 +6999,19 @@ reload:
* There was no time updates on current iteration. */
Sleep for an incremental amount of time if none of the Rx queues
assigned to a PMD have at least half a batch of packets (i.e. 16 pkts)
on an polling iteration of the PMD.
Upon detecting the threshold of >= 16 pkts on an Rxq, reset the
sleep time to zero (i.e. no sleep).
Sleep time will be
Add Similar to IPv4 counterpart, introduce IPv6 load-balancer health
check support.
Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=2136094
Signed-off-by: Lorenzo Bianconi
---
Changes since v1:
- fix potential crash in ovn-northd
- improve documentation
---
controller/pinctrl.c|
Some control protocols are used to maintain link status between
forwarding engines (e.g. LACP). When the system is not sized properly,
the PMD threads may not be able to process all incoming traffic from the
configured Rx queues. When a signaling packet of such protocols is
dropped, it can cause
> On Tue, Nov 22, 2022 at 12:54 PM Lorenzo Bianconi
> wrote:
> >
> > Add Similar to IPv4 counterpart, introduce IPv6 load-balancer health
> > check support.
> >
> > Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=2136094
> > Signed-off-by: Lorenzo Bianconi
>
> Hi Lorenzo,
>
> Thanks
References: <20221216155054.986464-6-simon.hor...@corigine.com>
Bleep bloop. Greetings Simon Horman, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected
References: <20221216155054.986464-5-simon.hor...@corigine.com>
Bleep bloop. Greetings Simon Horman, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected
References: <20221216155054.986464-4-simon.hor...@corigine.com>
Bleep bloop. Greetings Simon Horman, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected
References: <20221216155054.986464-3-simon.hor...@corigine.com>
Bleep bloop. Greetings Simon Horman, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected
References: <20221216155054.986464-2-simon.hor...@corigine.com>
Bleep bloop. Greetings Simon Horman, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected
From: Peng Zhang
OVS-DPDK meters are created in advance and OpenFlow rules refer to them by
their unique ID. A new API is used to offload them. By calling the API,
meters are created and try to be offload to all ports in the bridge.
Signed-off-by: Peng Zhang
Signed-off-by: Jin Liu
---
From: Peng Zhang
Add support of DPDK meter action logic.
Signed-off-by: Peng Zhang
Signed-off-by: Jin Liu
---
lib/netdev-offload-dpdk.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/lib/netdev-offload-dpdk.c b/lib/netdev-offload-dpdk.c
index 26c21f270a47..aeb5af05a8d9
From: Peng Zhang
Add the meter algorithms. DPDK meter support three algorithms,
and OVS also can support these algorithms.
Signed-off-by: Peng Zhang
Signed-off-by: Jin Liu
---
lib/netdev-dpdk.c | 58 +--
1 file changed, 51 insertions(+), 7
From: Peng Zhang
This commit adds support for OVS-DPDK with -DALLOW_EXPERIMENTAL_API.
Tunnel offloads and Meter offloads are experimental APIs in DPDK. To
enable these features, compile need add -DALLOW_EXPERIMENTAL_API. So
in workflow, we also need need the new test with
From: Peng Zhang
Add API to offload DPDK meter to HW, and the corresponding functions to call
the DPDK meter callbacks from all the registered flow API providers.
The interfaces are like those related to DPDK meter in dpif_class, in order
to pass necessary info to HW.
Signed-off-by: Peng Zhang
From: Peng Zhang
For dpif-netdev, meters are mapped by DPDK meter with one-to-one
relationship. Implement meter offload API to set/get/del
the DPDK meter.
Signed-off-by: Peng Zhang
Signed-off-by: Jin Liu
---
lib/netdev-dpdk.c | 199 ++
Hi,
this series adds support for DPDK meter HW offload
* Patch 1/6: Add netdev provider API for HW offload of DPDK meters
* Patch 2/6: Add DPIF API to offload OpenFlow meters to DPDK
* Patch 3/6: Implement netdev provider API for HW offload of DPDK meters
* Patch 4/6: Add more DPDK meter
In 59e8cb8a053d ("rhel: Move conf.db to /var/lib/openvswitch, using symlinks.")
conf.db is created as empty file in /var/lib/openvswitch, if it doesn't
exists, but this prevent ovsdb-server to start.
This commit changes the previous behaviour to set
/var/lib/openvswitch owner to
On 16 Dec 2022, at 8:56, Peng He wrote:
> From: Peng He
> To: Eelco Chaudron
> Cc: Ilya Maximets , ovs-dev@openvswitch.org
> Subject: Re: [ovs-dev v7 1/3] ofproto-dpif-upcall: fix push_dp_ops
> Date: Fri, 16 Dec 2022 15:56:32 +0800
>
> Eelco Chaudron 于2022年12月13日周二 20:36写道:
>
>>
>>
>> On 10
To make it easier to add flows to this stage, refactor the function.
This also has the benefit that we should see fewer allocations due to
rearranging how we create flows and how we manipulate the match string.
Signed-off-by: Ales Musil
---
northd/northd.c | 456
On 12/15/22 18:38, Dumitru Ceara wrote:
On 12/15/22 22:43, Mark Michelson wrote:
Signed-off-by: Mark Michelson
---
I more-or-less randomized the time of day since this will be at some
point early tomorrow for me. I plan to regenerate the patch with the
correct time when I actually push the
Ales Musil writes:
> Add extension that allows to flush connections from CT
> by specifying fields that the connections should be
> matched against. This allows to match only some fields
> of the connection e.g. source address for orig direrction.
>
> Reported-at:
Thanks Dumitru!
Regards,
Vladislav Odintsov
> On 16 Dec 2022, at 15:17, Dumitru Ceara wrote:
>
> Hi Vladislav,
>
> I pushed the series to main branch and branch-22.12. I also backported
> the first 4 patches all the way down to branch-22.03.
>
> Thanks a lot for the fixes (and thanks Numan
On Fri, Dec 16, 2022 at 1:01 PM Paolo Valerio wrote:
> Ales Musil writes:
>
> > Add extension that allows to flush connections from CT
> > by specifying fields that the connections should be
> > matched against. This allows to match only some fields
> > of the connection e.g. source address for
Add extension that allows to flush connections from CT
by specifying fields that the connections should be
matched against. This allows to match only some fields
of the connection e.g. source address for orig direrction.
Reported-at: https://bugzilla.redhat.com/2120546
Signed-off-by: Ales Musil
Currently, the CT can be flushed by dpctl only be specifying
the whole 5-tuple. This is not very convenient when there are
only some fields known to the user of CT flush. Add new struct
ofputil_ct_match which represents the generic filtering that can
be done for CT flush. The match is done only on
Add extension that will allow to flush
connection from CT specified by full
orig 5-tuple or partial match that combines
orig or reply direction.
Ales Musil (2):
ofp, dpif: Allow CT flush based on partial match
openflow: Add extension to flush CT by generic match
NEWS
Hi Vladislav,
I pushed the series to main branch and branch-22.12. I also backported
the first 4 patches all the way down to branch-22.03.
Thanks a lot for the fixes (and thanks Numan for the review)!
Regards,
Dumitru
On 12/16/22 10:58, Vladislav Odintsov wrote:
> Hi Dumitru,
>
> Regards,
>
Ales Musil writes:
> Add extension that allows to flush connections from CT
> by specifying fields that the connections should be
> matched against. This allows to match only some fields
> of the connection e.g. source address for orig direrction.
>
> Reported-at:
Ales Musil writes:
> Currently, the CT can be flushed by dpctl only be specifying
> the whole 5-tuple. This is not very convenient when there are
> only some fields known to the user of CT flush. Add new struct
> ofputil_ct_match which represents the generic filtering that can
> be done for CT
Hello:
This patch was applied to netdev/net.git (master)
by David S. Miller :
On Thu, 15 Dec 2022 15:46:33 +0100 you wrote:
> The commit mentioned below causes the ovs_flow_tbl_lookup() function
> to be called with the masked key. However, it's supposed to be called
> with the unmasked key. This
Hi Dumitru,
Regards,
Vladislav Odintsov
> On 16 Dec 2022, at 02:16, Dumitru Ceara wrote:
>
> On 12/15/22 22:30, Vladislav Odintsov wrote:
>> Thanks Numan for the review.
>>
>> It seems that for some reason appeared a memory leak, which constantly
>> reproduces.
>
> Do you mean this one?
>
On 12/16/22 08:20, Ales Musil wrote:
> On Fri, Dec 16, 2022 at 12:32 AM Dumitru Ceara wrote:
>
>> On 12/7/22 16:34, Ales Musil wrote:
>>> In order to have the SNAT action available for
>>> related traffic store the flag in CT register.
>>>
>>> Extend the ct_lb and ct_lb_mark action to
>>> allow
36 matches
Mail list logo