On Fri, Jan 15, 2021 at 7:31 AM Eric Li wrote:
>
> Hi All,
>
> We have a setup with br-int and br-tun similar to openstack setup. Using an
> openflow rule to forward a vxlan tunnelled packet to another machine, we
> set the exact destination IP and destination mac under a group rule.
>
> We are
On Fri, Jan 15, 2021 at 5:20 AM Aaron Conole wrote:
>
> Hi Tonghao Xhang,
>
> xiangxia.m@gmail.com writes:
>
> > From: Tonghao Zhang
> >
> > The same icmp packet may traverse conntrack module more than once.
> > Or same icmp packets traverse contranck module in orderly.
> >
> > Don't change
> -Original Message-
> From: Aaron Conole [mailto:acon...@redhat.com]
> Sent: Thursday, January 14, 2021 11:23 PM
> To: Li,Rongqing
> Cc: ovs-dev@openvswitch.org; William Tu
> Subject: Re: [ovs-dev] [PATCH][v2] conntrack: Fix conntrack tw expiration
>
> "Li,Rongqing" writes:
>
> >
>
Hi All,
We have a setup with br-int and br-tun similar to openstack setup. Using an
openflow rule to forward a vxlan tunnelled packet to another machine, we
set the exact destination IP and destination mac under a group rule.
We are seeing ARP requests for the destination IP unexpectedly. I
Introduce bfd info to lr-route-list command
Signed-off-by: Lorenzo Bianconi
---
tests/ovn-northd.at | 1 +
utilities/ovn-nbctl.c | 5 +
2 files changed, 6 insertions(+)
diff --git a/tests/ovn-northd.at b/tests/ovn-northd.at
index 91eb9a3d1..b5a39b1fc 100644
--- a/tests/ovn-northd.at
+++
Hi Tonghao Xhang,
xiangxia.m@gmail.com writes:
> From: Tonghao Zhang
>
> The same icmp packet may traverse conntrack module more than once.
> Or same icmp packets traverse contranck module in orderly.
>
> Don't change stats to CS_ESTABLISHED before receiving reply or related
> packets.
>
>
Ilya Maximets writes:
> On 12/23/20 12:23 PM, xiangxia.m@gmail.com wrote:
>> From: Tonghao Zhang
>>
>> The same icmp packet may traverse conntrack module more than once.
>> Or same icmp packets traverse contranck module in orderly.
>>
>> Don't change stats to CS_ESTABLISHED before
> When any PMD auto load balance parameters change, it is useful
> to also log if the feature is enabled or disabled.
>
> |dpif_netdev|INFO|PMD auto load balance pmd load threshold changed to
> 70%
> |dpif_netdev|INFO|PMD auto load balance is disabled
>
> Signed-off-by: Kevin Traynor
>
> From: Christophe Fontaine
>
> Two important parts of how PMD auto load balance operates are how
> loaded a core needs to be and how much improvement is estimated
> before a PMD auto load balance can trigger.
>
> Previously they were hardcoded to 95% loaded and 25% variance
> improvement.
>
>
> Previously if the parameter for the PMD auto load balance minimum
> interval was changed at runtime, it was not logged unless the
> PMD auto load balance feature was also changed to enabled.
>
> Log the parameter anytime it changes, and use minutes when it is
> logged as that is the user input
On 12/23/20 12:23 PM, xiangxia.m@gmail.com wrote:
> From: Tonghao Zhang
>
> The same icmp packet may traverse conntrack module more than once.
> Or same icmp packets traverse contranck module in orderly.
>
> Don't change stats to CS_ESTABLISHED before receiving reply or related
> packets.
> From: Anton Ivanov
>
> The calling convention for the per-od/per-op routines is that
> any data is passed as a part of the lsi struct. This way the
> functions can be used in both sequential and parallel builds.
>
> Signed-off-by: Anton Ivanov
> ---
Tested-by: Lorenzo Bianconi
>
From: Anton Ivanov
Datapaths, ports, igmp groups and load balancers can now
be iterated over in parallel in order to speed up the lflow
generation. This decreases the time needed to generate the
logical flows by a factor of 4+ on a 6 core/12 thread CPU
without datapath groups - from 0.8-1
From: Anton Ivanov
Signed-off-by: Anton Ivanov
---
northd/ovn-northd.c | 2 ++
ovn-nb.xml | 13 +
2 files changed, 15 insertions(+)
diff --git a/northd/ovn-northd.c b/northd/ovn-northd.c
index 5e1d129d5..6a2354562 100644
--- a/northd/ovn-northd.c
+++
From: Anton Ivanov
The calling convention for the per-od/per-op routines is that
any data is passed as a part of the lsi struct. This way the
functions can be used in both sequential and parallel builds.
Signed-off-by: Anton Ivanov
---
northd/ovn-northd.c | 12
1 file changed, 8
From: Anton Ivanov
This adds a set of functions and macros intended to process
hashes in parallel.
The principles of operation are documented in the fasthmap.h
If these one day go into the OVS tree, the OVS tree versions
would be used in preference.
Signed-off-by: Anton Ivanov
---
On 9/11/19 11:18 PM, Yifeng Sun wrote:
> Valgrind reported:
>
> 1210: ofproto-dpif - continuation after clone
>
> ==32205== 4,392 (1,440 direct, 2,952 indirect) bytes in 12 blocks are
> definitely lost in loss record 359 of 362
> ==32205==at 0x4C2DB8F: malloc (in
>
"Li,Rongqing" writes:
>
>
>
>
>> -Original Message-
>
>> From: Aaron Conole [mailto:acon...@redhat.com]
>
>> Sent: Friday, January 08, 2021 11:15 PM
>
>> To: Li,Rongqing
>
>> Cc: ovs-dev@openvswitch.org; William Tu
>
>> Subject: Re: [ovs-dev] [PATCH][v2] conntrack: Fix conntrack tw
On 14/01/2021 11:54, Ilya Maximets wrote:
On 1/11/21 10:51 AM, anton.iva...@cambridgegreys.com wrote:
From: Anton Ivanov
This adds a set of functions and macros intended to process
hashes in parallel.
The principles of operation are documented in the fasthmap.h
If these one day go into the
I see that Ilya has some comments, so those need addressing, but aside
from that, I reviewed and
Acked-by: Mark Michelson
On 1/11/21 4:51 AM, anton.iva...@cambridgegreys.com wrote:
From: Anton Ivanov
This adds a set of functions and macros intended to process
hashes in parallel.
The
adds "emc entries" to "ovs-appctl dpif-netdev/pmd-stats-show" in order
to show the number of alive entries.
Signed-off-by: Paolo Valerio
---
NEWS | 2 ++
lib/dpif-netdev-perf.h | 2 ++
lib/dpif-netdev.c | 76 +++---
tests/pmd.at
On 1/11/21 10:51 AM, anton.iva...@cambridgegreys.com wrote:
> From: Anton Ivanov
>
> This adds a set of functions and macros intended to process
> hashes in parallel.
>
> The principles of operation are documented in the fasthmap.h
>
> If these one day go into the OVS tree, the OVS tree
On 1/14/2021 11:09 AM, Finn, Emma wrote:
External email: Use caution opening links or attachments
-Original Message-
From: dev On Behalf Of Eli Britstein
Sent: Sunday 3 January 2021 11:55
To: d...@openvswitch.org; Ilya Maximets
Cc: Eli Britstein
Subject: [ovs-dev] [PATCH 2/4]
> -Original Message-
> From: dev On Behalf Of Eli Britstein
> Sent: Sunday 3 January 2021 11:55
> To: d...@openvswitch.org; Ilya Maximets
> Cc: Eli Britstein
> Subject: [ovs-dev] [PATCH 2/4] netdev-offload-dpdk: Support IPv4
> fragmentation types
>
> Support IPv4 fragmentation
24 matches
Mail list logo