On Wed, Apr 13, 2022 at 05:30:19PM -0400, Rosemarie O'Riorden wrote:
> When OVS sees a tunnel push with a nested list next, it will not
> clone the packet, as a clone is not needed. However, a clone action will
> still be created with the tunnel push encapulated inside. There is no
> need to
On Wed, Apr 13, 2022 at 8:48 AM Numan Siddique wrote:
>
> On Wed, Apr 13, 2022 at 2:34 AM Han Zhou wrote:
> >
> > During incremental flow processing, we track the OVS desired flow
> > changes so that we can incrementally install them to OVS. The function
> > merge_tracked_flows() is to merge the
Updated 12.2 to 12.3 and 11.4 to 13.0.
'pkg update' fails on 12.2. 11.4 has reached end of life.
Signed-off-by: Rosemarie O'Riorden
---
.cirrus.yml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/.cirrus.yml b/.cirrus.yml
index a7ae793bc..a4d2a5bbc 100644
---
> On Wed, Mar 23, 2022 at 4:22 PM Lorenzo Bianconi <
> lorenzo.bianc...@redhat.com> wrote:
> >
> > Introduce the capability to run a recompute just on updated nodes in case
> > of an incremental processing abort (e.g. if the controller is not able to
> > write on the sb db and the change can't be
Please disregard the "1/3" in the title; it is an error. This is just a
single patch.
Rosemarie O'Riorden
On 4/13/22 17:30, Rosemarie O'Riorden wrote:
> When OVS sees a tunnel push with a nested list next, it will not
> clone the packet, as a clone is not needed. However, a clone action will
>
When OVS sees a tunnel push with a nested list next, it will not
clone the packet, as a clone is not needed. However, a clone action will
still be created with the tunnel push encapulated inside. There is no
need to create the clone action in this case, as extra parsing will need
to be performed,
On 4/13/22 15:52, Terry Wilson wrote:
> Before 46d44cf3b, it was technically possible to assign a monitor
> condition directly to Idl.tables[table_name].condition. If done
> before the connection was established, it would successfully apply
> the condition (where cond_change() actually would
Hi Cian,
Thanks for the patch, comments inline.
> Checking for AVX512BW and AVX512DQ separately will allow the compiler to
> generate some AVX512 code where it is supported. For example, in GCC 4.9
> where there is just support for AVX512F, this patch will allow the
> AVX512 DPIF to be built.
>
On Wed, Apr 13, 2022 at 2:36 AM Han Zhou wrote:
>
> On Mon, Apr 11, 2022 at 2:05 PM Numan Siddique wrote:
> >
> > On Sat, Feb 5, 2022 at 12:12 AM Han Zhou wrote:
> > >
> > > On Fri, Feb 4, 2022 at 7:58 AM Mark Michelson
> wrote:
> > > >
> > > > As far as I can tell, this looks correct.
> > > >
On Wed, Apr 13, 2022 at 2:34 AM Han Zhou wrote:
>
> During incremental flow processing, we track the OVS desired flow
> changes so that we can incrementally install them to OVS. The function
> merge_tracked_flows() is to merge the "delete and add/update" for the
> same flows, to avoid unnecessary
On Tue, Apr 12, 2022 at 8:06 PM Ihar Hrachyshka wrote:
>
> There's a discussion to have on the intended behavior of a port with 2+
> chassis when the switch is attached to localnet.
>
> In general, the patch series makes all chassis switch to tunneling when
> multiple chassis are set. (See patch
Before 46d44cf3b, it was technically possible to assign a monitor
condition directly to Idl.tables[table_name].condition. If done
before the connection was established, it would successfully apply
the condition (where cond_change() actually would fail).
Although this wasn't meant to be supported,
On 4/13/22 15:15, Terry Wilson wrote:
> On Wed, Apr 13, 2022 at 3:06 AM Dumitru Ceara wrote:
>>
>> On 4/12/22 21:52, Terry Wilson wrote:
>>> Before 46d44cf3b, it was technically possible to assign a monitor
>>> condition directly to Idl.tables[table_name].condition. If done
>>> before the
Shared memory mempools may be currently be shared between DPDK
ports based on port MTU and NUMA. With some hint from the user
we can increase the sharing on MTU and hence reduce memory
consumption in many cases.
For example, a port with MTU 9000, uses a mempool with an
mbuf size based on 9000
No change in behaviour. This is so the MTU to mbuf size
calculations can be done in netdev_dpdk or dpdk code.
Signed-off-by: Kevin Traynor
---
lib/dpdk-stub.c | 8
lib/dpdk.c| 17 +
lib/dpdk.h| 18 ++
lib/netdev-dpdk.c | 32
This patchset optimizes for two cases when using shared mempools.
If there are ports with different MTUs, that usually leads
to multiple shared mempools being created because mempool
mbuf size and hence creation is based from MTU.
In fact, a port with a smaller MTU could share a mempool with
On Wed, Apr 13, 2022 at 3:06 AM Dumitru Ceara wrote:
>
> On 4/12/22 21:52, Terry Wilson wrote:
> > Before 46d44cf3b, it was technically possible to assign a monitor
> > condition directly to Idl.tables[table_name].condition. If done
> > before the connection was established, it would successfully
On 4/12/22 21:52, Terry Wilson wrote:
> Before 46d44cf3b, it was technically possible to assign a monitor
> condition directly to Idl.tables[table_name].condition. If done
> before the connection was established, it would successfully apply
> the condition (where cond_change() actually would
On Mon, Apr 11, 2022 at 2:05 PM Numan Siddique wrote:
>
> On Sat, Feb 5, 2022 at 12:12 AM Han Zhou wrote:
> >
> > On Fri, Feb 4, 2022 at 7:58 AM Mark Michelson
wrote:
> > >
> > > As far as I can tell, this looks correct.
> > >
> > > Acked-by: Mark Michelson
> >
> > Thanks Mark. I applied it to
During incremental flow processing, we track the OVS desired flow
changes so that we can incrementally install them to OVS. The function
merge_tracked_flows() is to merge the "delete and add/update" for the
same flows, to avoid unnecessary changes to OVS when flows are deleted
but added back in
20 matches
Mail list logo