Having trouble viewing this email? Please follow this link to see the messaged
emailed to you.
(Unsubscribe Instructions Here)
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Having trouble viewing this email? Please follow this link to see the messaged
emailed to you.
Product Image
Product Image
(Unsubscribe Instructions Here)
___
dev mailing list
d...@openvswitch.org
Viernes 06 de Noviembre | Horario de 10:00 a 17:00 hrs. | (hora del centro de
México)
- Curso de redacción para profesionistas -
¿De qué hablaremos?
Proporcionar a los participantes guías para una correcta redacción de textos
que sean claros, concisos y entendibles
para el ámbito
On Thu, 29 Oct 2020 15:53:21 +0100 Eelco Chaudron wrote:
> Silence suspicious RCU usage warning in ovs_flow_tbl_masks_cache_resize()
> by replacing rcu_dereference() with rcu_dereference_ovsl().
>
> In addition, when creating a new datapath, make sure it's configured under
> the ovs_lock.
>
>
Bleep bloop. Greetings Harry van Haaren, 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 80 characters long (recommended limit is 79)
#88 FILE:
Bleep bloop. Greetings Harry van Haaren, 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:
ERROR: C99 style comment
#324 FILE: lib/dpif-netdev.c:1002:
//void *new_dpif_func =
Bleep bloop. Greetings Harry van Haaren, 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 89 characters long (recommended limit is 79)
WARNING: Line lacks
Bleep bloop. Greetings Harry van Haaren, 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:
ERROR: Improper whitespace around control block
#215 FILE:
Bleep bloop. Greetings Harry van Haaren, 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:
ERROR: Inappropriate bracing around statement
#50 FILE: lib/dpdk.c:635:
if
This commit adds the AVX512 implementation of DPIF functionality,
specifically the dp_netdev_input_outer_avx512 function. This function
only handles outer (no re-circulations), and is optimized to use the
AVX512 ISA for packet batching and other DPIF work.
Sparse is not able to handle the AVX512
This commit implements larger subtable searches in avx512. A limitation
of the previous implementation was that up to 8 blocks of miniflow
data could be matched on (so a subtable with 8 blocks was handled
in avx, but 9 blocks or more would fall back to scalar/generic).
This limitation is removed
This commit adds a new command to allow the user to switch
the active DPIF implementation at runtime. A probe function
is executed before switching the DPIF implementation, to ensure
the CPU is capable of running the ISA required. For example, the
below code will switch to the AVX512 enabled DPIF
This commit refactors the function names from netdev_*
namespace to the dpcls_* namespace, as they are only used
by dpcls code. With the name change, it becomes more obvious
that the functions belong to dpcls functionality, and in the
dpif-netdev-private-dpcls.h header file.
Signed-off-by: Harry
This commit moves the dp_netdev_flow struct from dpif-netdev.c
to the dpif-netdev-private.h file. No code changes are made.
Signed-off-by: Harry van Haaren
---
lib/dpif-netdev-private.h | 96 +++
lib/dpif-netdev.c | 94
Split the very large file dpif-netdev.c and the datastructures
it contains into multiple header files. Each header file is
responsible for the datastructures of that component.
This logical split allows better reuse and modularity of the code,
and reduces the very large file dpif-netdev.c to be
This commit moves the pmd_try_optimize function to a more
appropriate location in the file - currently it sits in the
DPCLS section, which is not its correct home.
Signed-off-by: Harry van Haaren
---
lib/dpif-netdev.c | 146 +++---
1 file changed, 73
v2 updates:
- Includes DPIF command switching at runtime
- Includes AVX512 DPIF implementation
- Includes some partially related changes (can be split out of set?)
--- netdev output action optimization
--- avx512 dpcls 16-block support optimization
Hi OVS Community,
This patchset is a v2 for
This commit adds a function pointer to the pmd thread data structure,
giving the pmd thread flexibility in its dpif-input function choice.
This allows choosing of the implementation based on ISA capabilities
of the runtime CPU, leading to optimizations and higher performance.
Signed-off-by: Harry
This commit moves the datapath lookup functions required for
hardware offload to a seperate file. This allows other DPIF
implementations to access the lookup functions, encouraging
code reuse.
Signed-off-by: Harry van Haaren
---
v2: Fixed copyright header
---
lib/automake.mk|
As a small optimization, this patch caches the result of a CPU ISA
check from DPDK. Particularly in the case of running the DPCLS
autovalidator (which repeatedly probes subtables) this reduces
the amount of CPU ISA lookups from the DPDK level.
By caching them at the OVS/dpdk.c level, the ISA
This commit optimizes the output action, by enabling the compiler to
optimize the code better through reducing code complexity.
The core concept of this optimization is that the array-length checks
have already been performed above the copying code, so can be removed.
Removing of the per-packet
Me da mucho gusto saludarte.
Es, para mí, un placer poder invitarte a nuestro Curso en Línea "Excel
Intermedio", que se estará
llevando a cabo los días 7, 14 y 21 de Noviembre con un horario de 10:00 a
14:00 hrs.(hora del centro de México), con
un total de 12 hrs.
Con este curso de Excel
Having trouble viewing this email? Please follow this link to see the messaged
emailed to you.
Product Image
Product Image
Product Image
Product Image
(Unsubscribe Instructions Here)
(Unsubscribe Instructions Here)
___
dev mailing list
The question is whether there is any interest in continuing to support
the OVS out-of-tree (OOT) kernel driver or should we deprecate it? The
latest kernel support for the OOT driver is up to 5.8.x There seems to
be little interest that I can tell in using the OOT driver. The main
distros
Hi Yi,
Thanks for the patch and sorry the delay to review it.
See my comments in line.
Thanks,
fbl
On Fri, Aug 07, 2020 at 06:56:45PM +0800, yang_y...@163.com wrote:
> From: Yi Yang
>
> Many NICs can support VXLAN TSO which can help
> improve across-compute-node VM-to-VM performance
> in
Bleep bloop. Greetings Gaetan Rivet, 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 97 characters long (recommended limit is 79)
#52 FILE:
Bleep bloop. Greetings Gaetan Rivet, 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 sign-offs from developers who are not authors or co-authors
or
On 28/10/20 02:58 +0100, Gaëtan Rivet wrote:
[...]
> > >
> > >> +}
> > >> }
> > >> ovs_mutex_unlock(>mutex);
> > >>
> > >> @@ -1898,6 +1918,7 @@ netdev_dpdk_set_config(struct netdev *netdev,
> > >> const struct smap *args,
> > >> {RTE_FC_RX_PAUSE, RTE_FC_FULL}
I've invited you to fill out the following form:
Untitled form
To fill it out, visit:
https://docs.google.com/forms/d/e/1FAIpQLScuNN46De4NTNDuI_3Rm2L6CNABd5Ra0TyGG6ZxgVbAw2h7Ug/viewform?vc=0c=0w=1flr=0usp=mail_form_link
Hi,
Hope I am not intruding on your space here.
If you are interested in
v4: fix Kevin's and Ilya's comments.
v3: fix Ilya's comments.
v2: fix 0-day bot issues in 2/2.
Hello Ilya,
Following your suggestion, here is a small patch adding the ability to
configure the
MAC address of DPDK VF representors. As said off-ML, I've used the options
column
instead of
From: Ilya Maximets
It is possible to set the MAC address of DPDK ports by calling
rte_eth_dev_default_mac_addr_set(). OvS does not actually call
this function for non-internal ports, but the implementation is
exposed to be used in a later commit.
Signed-off-by: Ilya Maximets
Signed-off-by:
In some cloud topologies, using DPDK VF representors in guest requires
configuring a VF before it is assigned to the guest.
A first basic option for such configuration is setting the VF MAC
address. Add a key 'dpdk-vf-mac' to the 'options' column of the Interface
table.
This option can be used
> On Thu, Oct 22, 2020 at 12:57 PM Eli Britstein wrote:
> >
> > In sparse commit [1], __ATOMIC_* defines were introduced, which cause
> > redefinition errors. Commits [2],[3] introduced builtin __atomic_*
> > functions that are defined in OVS.
> > Wrap OVS defines with #ifndef to fix it. We
On Fri, Oct 30, 2020 at 3:32 PM Dumitru Ceara wrote:
>
> On 10/30/20 10:26 AM, Dumitru Ceara wrote:
> > On 10/30/20 10:17 AM, Numan Siddique wrote:
> >> On Fri, Oct 23, 2020 at 1:37 PM Dumitru Ceara wrote:
> >>>
> >>> Do not assume 'ofport' is unique for all OVS interfaces in the system.
> >>>
On 10/30/20 10:26 AM, Dumitru Ceara wrote:
> On 10/30/20 10:17 AM, Numan Siddique wrote:
>> On Fri, Oct 23, 2020 at 1:37 PM Dumitru Ceara wrote:
>>>
>>> Do not assume 'ofport' is unique for all OVS interfaces in the system. This
>>> is true only for interfaces within the same OVS bridge. Also,
On 10/30/20 10:17 AM, Numan Siddique wrote:
> On Fri, Oct 23, 2020 at 1:37 PM Dumitru Ceara wrote:
>>
>> Do not assume 'ofport' is unique for all OVS interfaces in the system. This
>> is true only for interfaces within the same OVS bridge. Also, only decode
>> br-int related interfaces.
>>
>>
On Fri, Oct 23, 2020 at 1:37 PM Dumitru Ceara wrote:
>
> Do not assume 'ofport' is unique for all OVS interfaces in the system. This
> is true only for interfaces within the same OVS bridge. Also, only decode
> br-int related interfaces.
>
> Also, fix printing of potential duplicate UUIDs
37 matches
Mail list logo
