Signed-off-by: Ihar Hrachyshka
---
tests/ovn.at | 7 +++
1 file changed, 7 insertions(+)
diff --git a/tests/ovn.at b/tests/ovn.at
index bfaa41962..e2d1d993e 100644
--- a/tests/ovn.at
+++ b/tests/ovn.at
@@ -14012,6 +14012,7 @@ AT_CLEANUP
OVN_FOR_EACH_NORTHD([
AT_SETUP([options:multiple
Before the patch, for switches with a localnet port,
- traffic to a multichassis port was funneled through tunnels; but
- traffic from a multichassis port was sent through localnet.
This is not optimal because:
- bidirectional sessions are sent through two separate paths;
- leaking multichassis
Hi Xavier,
Thanks a bunch for fixing this. I have a small suggestion below
On 6/22/22 11:02, Xavier Simonart wrote:
The following test cases were sometimes failing, (mainly) for the same reason
i.e. packet lost as being sent before patch ports were installed.
- 2 HVs, 2 LS, switching between
On 4/12/22 13:49, Christophe Fontaine wrote:
> This config param allows the delivery of broadcast and multicast packets
> to the secondary interface of non-lacp bonds, equivalent to the option
> "all_slaves_active" for kernel bonds.
>
> Reported-at:
In large scale scenarios this option hugely reduces the size of the
Southbound database positively affecting end to end performance. In
such scenarios there's no real reason to ever disable datapath groups.
In lower scale scenarios any potential overhead due to logical datapath
groups is, very
On 6/18/22 10:32, Lorenzo Bianconi wrote:
Hi Lorenzo, I have a few comments below
On 6/10/22 13:49, Lorenzo Bianconi wrote:
Match the drop flow for stateless dnat_and_snat flow in S_ROUTER_IN_GW_REDIRECT
stage just if allowed_ext_ips or exempted_ext_ips conditions do not
match since it breaks
Bleep bloop. Greetings Terry Wilson, 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: Line is 98 characters long (recommended limit is 79)
#97 FILE:
It is common to pass ovn-ctl options via an /etc/sysconfig file.
It would be useful to be able to pass custom --remote options or
additional DBs to listen to via this file. This would give end
users the ability to have more fine-grained control without
having to modify ovn-ctl.
Signed-off-by:
Bleep bloop. Greetings Terry Wilson, 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: Line has non-spaces leading whitespace
#27 FILE: utilities/ovn-ctl:315:
set
It is common to pass ovn-ctl options via an /etc/sysconfig file.
It would be useful to be able to pass custom --remote options or
additional DBs to listen to via this file. This would give end
users the ability to have more fine-grained control without
having to modify ovn-ctl.
Signed-off-by:
On 6/23/22 18:46, Ilya Maximets wrote:
> On 6/23/22 17:39, David Marchand wrote:
>> On Thu, Jun 23, 2022 at 3:33 PM Van Haaren, Harry
>> wrote:
>>>
-Original Message-
From: dev On Behalf Of Ales Musil
Sent: Thursday, June 23, 2022 1:41 PM
To: d...@openvswitch.org
On 6/23/22 17:39, David Marchand wrote:
> On Thu, Jun 23, 2022 at 3:33 PM Van Haaren, Harry
> wrote:
>>
>>> -Original Message-
>>> From: dev On Behalf Of Ales Musil
>>> Sent: Thursday, June 23, 2022 1:41 PM
>>> To: d...@openvswitch.org
>>> Cc: david.march...@redhat.com
>>> Subject:
On Thu, Jun 23, 2022 at 3:33 PM Van Haaren, Harry
wrote:
>
> > -Original Message-
> > From: dev On Behalf Of Ales Musil
> > Sent: Thursday, June 23, 2022 1:41 PM
> > To: d...@openvswitch.org
> > Cc: david.march...@redhat.com
> > Subject: [ovs-dev] [PATCH] cpu.c: Build cpu.c without any
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit includes infrastructure changes for enabling set_masked_X
> actions and also adds support for the AVX512 implementation of the
> eth_set_addrs action.
>
> Signed-off-by: Emma Finn
> ---
One small question on this piece of code:
+/* This
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> From: Kumar Amber
>
> This commit adds a new command to allow the user to enable the
> actions autovalidator by default at build time thus allowing for
> running unit test by default.
>
> $ ./configure --enable-actions-default-autovalidator
>
>
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit adds a new command to allow the user to switch
> the active action implementation at runtime. A probe function
> is executed before switching the implementation, to ensure
> the CPU is capable of running the ISA required.
>
> Usage:
> $
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit adds the AVX512 implementation of the action functionality.
>
> Usage:
> $ ovs-appctl dpif-netdev/action-impl-set avx512
>
> Signed-off-by: Emma Finn
> Acked-by: Harry van Haaren
> ---
> Documentation/ref/ovs-actions.7.rst | 26
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit removes the pop_vlan action from the large switch
> and creates a separate function for batched processing. A function
> pointer is also added to call the new batched function for the pop_vlan
> action.
>
> Signed-off-by: Emma Finn
>
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit introduced the auto-validation function which
> allows users to compare the batch of packets obtained from
> different action implementations against the linear
> action implementation.
>
> The autovalidator function can be triggered at
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit introduces the initial infrastructure required to allow
> different implementations for OvS actions. The patch introduces action
> function pointers which allows user to switch between different action
> implementations available. This will
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit adds the AVX512 implementation of the
> push_vlan action.
>
> Signed-off-by: Emma Finn
> ---
> lib/odp-execute-avx512.c | 37 +
> lib/odp-execute-private.c | 1 +
> lib/odp-execute.c | 22
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit adds the AVX512 implementation of the
> pop_vlan action.
>
> Signed-off-by: Emma Finn
> ---
> lib/odp-execute-avx512.c | 91
> 1 file changed, 91 insertions(+)
>
> diff --git
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> This commit adds support for the AVX512 implementation of the
> ipv4_set_addrs action as well as an AVX512 implementation of
> updating the checksums.
>
> Signed-off-by: Emma Finn
> ---
> lib/odp-execute-avx512.c | 210
On 14 Jun 2022, at 13:57, Emma Finn wrote:
> The IP checksum field was invalid in the input packets
> for some unit tests. The unit tests will still pass without
> a valid checksum, however we should still fix these.
>
> Signed-off-by: Emma Finn
> Acked-by: Eelco Chaudron
>
> ---
> This was
Hi Anurag,
On 23/06/2022 11:18, Anurag Agarwal wrote:
From: Jan Scheurich
Today dpif-netdev considers PMD threads on a non-local NUMA node for automatic
assignment of the rxqs of a port only if there are no local,non-isolated PMDs.
On typical servers with both physical ports on one NUMA node,
On 6/9/22 21:39, Mark Michelson wrote:
> I'm in agreement with Han and Numan that this is a good idea.
>
Thanks, Han, Mark, Numan!
> One thing that may be worth considering (maybe as a follow-up) is a
> re-think of parallelization when dp groups are always enabled. With dp
> groups disabled,
On 6/23/22 15:33, Van Haaren, Harry wrote:
>> -Original Message-
>> From: dev On Behalf Of Ales Musil
>> Sent: Thursday, June 23, 2022 1:41 PM
>> To: d...@openvswitch.org
>> Cc: david.march...@redhat.com
>> Subject: [ovs-dev] [PATCH] cpu.c: Build cpu.c without any assumptions about
>> CPU
> -Original Message-
> From: dev On Behalf Of Ales Musil
> Sent: Thursday, June 23, 2022 1:41 PM
> To: d...@openvswitch.org
> Cc: david.march...@redhat.com
> Subject: [ovs-dev] [PATCH] cpu.c: Build cpu.c without any assumptions about
> CPU flags
>
> The cpu.c was built with multiple
The cpu.c was built with multiple feature flags that might
not be available on all hosts. It manifested itself as
Illegal instruction with crashing on "shlx" instruction
which is part of the bmi2 extension, that might not be available
on all CPU that openvswitch runs on.
Move the cpu.c and cpu.h
Hi Dumitru,
thank you for reviewing this patch
On 6/8/22 12:25, Dumitru Ceara wrote:
On 5/31/22 11:33, Mohammad Heib wrote:
currently ovn ci only has one test case with the option
ovn-monitor-all enabled, this patch will add one more
execution with option ovn-monitor-all=true for each test
currently ovn ci only has one test case with the option
ovn-monitor-all enabled, this patch will add one more
execution with option ovn-monitor-all=true for each test case that
are wrapped by OVN_FOR_EACH_NORTHD macro.
This will more or less double the number of test cases.
It is possible to
change 'negotations' to 'negotiations'
Signed-off-by: yangchang
---
lib/lacp.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/lacp.h b/lib/lacp.h
index d731ae9..3c14862 100644
--- a/lib/lacp.h
+++ b/lib/lacp.h
@@ -24,7 +24,7 @@
/* LACP Protocol Implementation. */
From: Jan Scheurich
Today dpif-netdev considers PMD threads on a non-local NUMA node for automatic
assignment of the rxqs of a port only if there are no local,non-isolated PMDs.
On typical servers with both physical ports on one NUMA node, this often
leaves the PMDs on the other NUMA node
Thanks for your feedback. I have addressed your comments and shall post the
updated patch shortly.
Regards,
Anurag
> -Original Message-
> From: lic...@chinatelecom.cn
> Sent: Wednesday, June 22, 2022 4:19 PM
> To: Anurag Agarwal
> Cc: Anurag Agarwal ; ovs-dev@openvswitch.org
>
Hello:
This patch was applied to netdev/net.git (master)
by Paolo Abeni :
On Tue, 21 Jun 2022 16:48:45 -0400 you wrote:
> When a packet enters the OVS datapath and does not match any existing
> flows installed in the kernel flow cache, the packet will be sent to
> userspace to be parsed, and a
> -Original Message-
> From: Pai G, Sunil
> Sent: Thursday 23 June 2022 08:01
> To: d...@openvswitch.org
> Cc: echau...@redhat.com; Finn, Emma ; Van Haaren, Harry
> ; Ferriter, Cian
> Subject: [PATCH] dpif-netdev: Simplify AVX512 build time checks to enhance
> readability.
>
> The
> -Original Message-
> From: Amber, Kumar
> Sent: Tuesday, May 24, 2022 12:39 PM
> To: ovs-dev@openvswitch.org
> Cc: f...@sysclose.org; echau...@redhat.com; i.maxim...@ovn.org; Van Haaren,
> Harry ; Ferriter, Cian ;
> Stokes, Ian ; Amber, Kumar
> Subject: [PATCH v2 5/5]
> -Original Message-
> From: Amber, Kumar
> Sent: Tuesday, May 24, 2022 12:39 PM
> To: ovs-dev@openvswitch.org
> Cc: f...@sysclose.org; echau...@redhat.com; i.maxim...@ovn.org; Van Haaren,
> Harry ; Ferriter, Cian ;
> Stokes, Ian ; Amber, Kumar
> Subject: [PATCH v2 4/5] dpif-netdev: Add
> -Original Message-
> From: Amber, Kumar
> Sent: Tuesday, May 24, 2022 12:39 PM
> To: ovs-dev@openvswitch.org
> Cc: f...@sysclose.org; echau...@redhat.com; i.maxim...@ovn.org; Van Haaren,
> Harry ; Ferriter, Cian ;
> Stokes, Ian ; Amber, Kumar
> Subject: [PATCH v2 3/5]
On 2022-06-01 10:52 AM, Eelco Chaudron wrote:
On 1 Jun 2022, at 9:02, Roi Dayan wrote:
On 2022-05-31 5:34 PM, Eelco Chaudron wrote:
When processing netlink messages, we should ignore unknown OVS_KEY_ATTR
as we can assume if newer attributes are present, they are backward
compatible.
> -Original Message-
> From: Amber, Kumar
> Sent: Tuesday, May 24, 2022 12:39 PM
> To: ovs-dev@openvswitch.org
> Cc: f...@sysclose.org; echau...@redhat.com; i.maxim...@ovn.org; Van Haaren,
> Harry ; Ferriter, Cian ;
> Stokes, Ian ; Amber, Kumar
> Subject: [PATCH v2 2/5] dpif-netdev:
> -Original Message-
> From: Amber, Kumar
> Sent: Tuesday, May 24, 2022 12:39 PM
> To: ovs-dev@openvswitch.org
> Cc: f...@sysclose.org; echau...@redhat.com; i.maxim...@ovn.org; Van Haaren,
> Harry ; Ferriter, Cian ;
> Stokes, Ian ; Amber, Kumar
> Subject: [PATCH v2 1/5] dpif-netdev:
On 2022-06-22 11:56 PM, Marcelo Ricardo Leitner wrote:
On Wed, Jun 22, 2022 at 11:10:17AM +0800, Tao Liu wrote:
On Tue, Jun 21, 2022 at 06:49:42AM -0700, Marcelo Ricardo Leitner wrote:
Hi,
On Tue, Jun 21, 2022 at 02:10:39PM +0800, Tao Liu wrote:
Bond master netdev may be created without a
On 21 Jun 2022, at 22:48, Rosemarie O'Riorden wrote:
> When a packet enters the OVS datapath and does not match any existing
> flows installed in the kernel flow cache, the packet will be sent to
> userspace to be parsed, and a new flow will be created. The kernel and
> OVS rely on each other
The preprocessor comparison string to check AVX512 capabilities are
lengthy and effecting user readability. Simpify this by aliasing the checks.
Suggested-by: Eelco Chaudron
Signed-off-by: Sunil Pai G
---
lib/dpif-netdev-private-dpif.c| 6 --
lib/dpif-netdev-private-extract.c | 3 +--
On 22 Jun 2022, at 18:22, Finn, Emma wrote:
> Hi Eelco,
>
> I've investigated the issue and resolved the failing unit tests.
> Diff's are provided below or if it's convenient I can send as patchset
> instead.
>
> Fix for 05/11: odp-execute: Add command to switch action implementation.
>
> diff
46 matches
Mail list logo