This series introduces a new hash-based Tx packets steering
mode alognside existing XPS and static modes. The goal is
to provide a mode where all the transmit queues are used,
whatever the number of PMD threads. This may be used with
Vhost-user ports, where the guest application driving the
Virtio
This patch adds Rx and Tx per-queue statistics. It will be
used to test hash-based Tx packet steering. Only "bytes",
and "packets" per-queue custom statistics are added, as
there are no global "errors" counters in netdev-dummy.
Signed-off-by: Maxime Coquelin
Reviewed-by: David Marchand
---
lib/
A boolean is currently used to differenciate between the
static and XPS Tx queue modes.
Since we are going to introduce a new steering mode, replace
this boolean with an enum.
This patch does not introduce functionnal changes.
Signed-off-by: Maxime Coquelin
Reviewed-by: David Marchand
---
lib
Hash-based Tx steering feature will enable steering Tx
packets on transmit queues based on their hashes. In order
to test the feature, it is needed to be able to get the
per-queue statistics for Vhost-user ports.
This patch introduces "bytes", "packets" and "error"
per-queue custom statistics for
This patch introduces a new test for Tx packets
steering modes. First test validates the static mode,
by checking that all packets are transmitted on a single
queue (single PMD thread), then it tests the same with
enabling hash based packet steering, ensuring packets
are transmitted on both queues.
This patch adds a new hash Tx steering mode that
distributes the traffic on all the Tx queues, whatever the
number of PMD threads. It would be useful for guests
expecting traffic to be distributed on all the vCPUs.
The idea here is to re-use the 5-tuple hash of the packets,
already computed to bui
On Tue, 4 Jan 2022, Jakub Kicinski wrote:
> On Tue, 4 Jan 2022 10:28:21 +0200 Paul Blakey wrote:
> > Netfilter conntrack maintains NAT flags per connection indicating
> > whether NAT was configured for the connection. Openvswitch maintains
> > NAT flags on the per packet flow key ct_state fiel
On 5 Jan 2022, at 3:12, Chris Mi wrote:
> Hi Eelco,
>
> Version 19 mainly fixes a bug that psample_sock is destroyed when last
> bridge is deleted.
> And it also addresses some of the minor comments in v18. I think there is no
> use
> to address all of them because if we need to change the dp
On 4 Jan 2022, at 17:52, Ilya Maximets wrote:
> On 12/6/21 17:57, Eelco Chaudron wrote:
>> Currently, if a flow reply results in a message which exceeds
>> the maximum reply size, it will assert OVS. This would happen
>> when OVN uses OpenFlow15 to add large flows, and they get read
>> using Op
Currently, if a flow reply results in a message which exceeds
the maximum reply size, it will assert OVS. This would happen
when OVN uses OpenFlow15 to add large flows, and they get read
using OpenFlow10 with ovs-ofctl.
This patch prevents this and adds a test case to make sure the
code behaves as
Currently, if multiple distributed gateway ports (DGP) are configured
on a logical router, NAT is disabled as part of commit 15348b7b
(northd: Multiple distributed gateway port support.)
This patch updates the behavior by selectively applying NAT rules at DGPs.
A NAT rule is applied on matching pa
References: <20220105100833.152201-1-sangana.abhi...@nutanix.com>
Bleep bloop. Greetings Abhiram Sangana, 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 84 ch
In conjunction with --nbdb-source and --sbdb-source this makes sandbox
troubleshooting of pre-existing deployments easier.
Signed-off-by: Dumitru Ceara
---
tutorial/ovs-sandbox | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tutorial/ovs-sandbox b/tutorial/ovs-sandb
ovndb-ctl deamon mode, the connection cannot be reconnected when
connection is broken, set inactivity probe interval to make it
reconnected
Signed-off-by: Wentao Jia
---
utilities/ovn-dbctl.c | 4
1 file changed, 4 insertions(+)
diff --git a/utilities/ovn-dbctl.c b/utilities/ovn-dbctl.
Even if it has no associated local OVS interface, for every port binding
of type 'LP_VIF' that is a parent lport of container lports, a 'struct
local_binding' object is created. When building flows to forward BUM
traffic keep this in mind when adding flows to table
OFTABLE_REMOTE_OUTPUT.
Reported
On 5 Jan 2022, at 10:43, Eelco Chaudron wrote:
> On 4 Jan 2022, at 17:52, Ilya Maximets wrote:
>
>> On 12/6/21 17:57, Eelco Chaudron wrote:
>>> Currently, if a flow reply results in a message which exceeds
>>> the maximum reply size, it will assert OVS. This would happen
>>> when OVN uses OpenFl
Currently, if a flow reply results in a message which exceeds
the maximum reply size, it will assert OVS. This would happen
when OVN uses OpenFlow15 to add large flows, and they get read
using OpenFlow10 with ovs-ofctl.
This patch prevents this and adds a test case to make sure the
code behaves as
On 1/3/22 11:19, Eelco Chaudron wrote:
> Hi Ilya,
>
> As you reviewed the v1, I’m wondering if this can get into the next release?
Hi. Sorry, this one fell through the cracks.
It seems to be a bug fix, so we'll need to backport it anyway.
I'll try to get to this patch in a near future.
Best reg
On 5 Jan 2022, at 15:35, Ilya Maximets wrote:
> On 1/3/22 11:19, Eelco Chaudron wrote:
>> Hi Ilya,
>>
>> As you reviewed the v1, I’m wondering if this can get into the next release?
>
> Hi. Sorry, this one fell through the cracks.
No problem, same here, I noticed it when picking up some relate
It seems Linux native tunnel configuration changed to enable
checksum by default and that causes the check-system-tso unit
test below to fail:
10: datapath - ping over vxlan tunnelFAILED (system-traffic.at:248)
That happens because userspace TSO doesn't support encapsulation
as mentioned in t
On Wed, 5 Jan 2022, Daniel Borkmann wrote:
> On 1/5/22 3:57 PM, Jamal Hadi Salim wrote:
> > On 2022-01-04 03:28, Paul Blakey wrote:
> > [..]
> >> --- a/include/linux/skbuff.h
> >> +++ b/include/linux/skbuff.h
> >> @@ -287,7 +287,9 @@ struct tc_skb_ext {
> >> __u32 chain;
> >> __u16 m
On 2022-01-04 03:28, Paul Blakey wrote:
[..]
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -287,7 +287,9 @@ struct tc_skb_ext {
__u32 chain;
__u16 mru;
__u16 zone;
- bool post_ct;
+ bool post_ct:1;
+ bool post_ct_snat:1;
+ bool post_c
On 1/5/22 3:57 PM, Jamal Hadi Salim wrote:
On 2022-01-04 03:28, Paul Blakey wrote:
[..]
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -287,7 +287,9 @@ struct tc_skb_ext {
__u32 chain;
__u16 mru;
__u16 zone;
- bool post_ct;
+ bool post_ct:1;
+ bool post_c
---
v4:
- Rebase to master
- Add ISA implementation of push_vlan action
---
v3:
- Refactored to fix unit test failures
- Removed some sign-off on commits
---
v2:
- Fix the CI build issues
---
This patchset introduces actions infrastructure changes
which allows the user to choose between different
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 allow for more performance and flexibility
so the us
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
---
lib/odp-execute-private.c | 19 +-
lib/odp
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:
$ ovs-appctl dpif-netdev/action-impl-set scalar
This commit
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 runtime using the
following command:
$ ovs-appctl dpif-net
From: Kumar Amber
Added separate test-case for ovs-actions get/set commands:
1023: PMD - ovs-actions configuration
The above added tests are to test the commands which are used
to either get or set the ovs-actions function pointers to
various different implementations like AVX512 or auto-validat
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
Signed-off-by: Kumar Amber
---
NEWS | 2 ++
acinc
This commit adds the AVX512 implementation of the pop_vlan action.
The implementation here is auto-validated by the miniflow
extract autovalidator, hence its correctness can be easily
tested and verified.
Signed-off-by: Emma Finn
---
NEWS | 1 +
lib/odp-execute-avx512.c |
This commit adds the AVX512 implementation of the action functionality.
Usage:
$ ovs-appctl dpif-netdev/action-impl-set avx512
Signed-off-by: Emma Finn
---
Documentation/topics/dpdk/bridge.rst | 25 ++
Documentation/topics/testing.rst | 20 +---
NEWS
This commit adds the AVX512 implementation of the push_vlan action.
The implementation here is auto-validated by the miniflow
extract autovalidator, hence its correctness can be easily
tested and verified.
Signed-off-by: Emma Finn
---
NEWS | 1 +
lib/odp-execute-avx512.c |
Acked-by: Mark Michelson
This is a new feature, but it's good for debugging, so should this be
backported to previous releases?
On 1/5/22 05:40, Dumitru Ceara wrote:
In conjunction with --nbdb-source and --sbdb-source this makes sandbox
troubleshooting of pre-existing deployments easier.
Si
Hi Dumitru,
Looks good to me.
Acked-by: Mark Michelson
On 1/5/22 08:05, Dumitru Ceara wrote:
Even if it has no associated local OVS interface, for every port binding
of type 'LP_VIF' that is a parent lport of container lports, a 'struct
local_binding' object is created. When building flows to
Hello Flavio,
Great patch, I think you really did a lot to improve the code here and
I think that's borne out by the consistent performance improvements
across multiple tests.
Regarding the 4% regression that Intel detected, I found the following
white paper to describe the "scatter" test:
https
In conjunction with --nbdb-source and --sbdb-source this makes sandbox
troubleshooting of pre-existing deployments easier.
Signed-off-by: Dumitru Ceara
---
v2:
- Add support for specifying a custom hostname.
---
tutorial/ovs-sandbox | 20 ++--
1 file changed, 18 insertions(+), 2
On 1/5/22 20:34, Mark Michelson wrote:
> Acked-by: Mark Michelson
>
Thanks for the review, Mark! However, while using this patch I realized
it's even better if we can also specify a custom hostname.
I posted a v2 with that added (sorry for the noise):
http://patchwork.ozlabs.org/project/ovn/p
The fuzzing target times out if the action list is too big. And we
don't really need to fully parse all the actions just to say that they
are too big in the end. So, check early and exit.
This is a pure performance optimization, so not adding a unit test.
All other code paths during the parsing
Hi,
I haven't done a full review of this patch, but I have noticed a problem
pretty early on when I started looking.
The new ip_in_lrp_networks() function that is added here is intended to
determine which l3dgw port to use for a particular NAT external address.
The problem is that there are
From: "grimlock.lw"
When Recving tcp stream form LOCAL port, and flows have a dp_hash group, linux
call skb_set_hash_from_sk to set skb->hash and skb->l4_hash, ovs use skb->hash
to select group bucket.
When tcp retransmission occurs,linux call sk_rethink_txhash to rehash skb->hash
of retransmi
Bleep bloop. Greetings grimlock.lw, 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: Author grimlock.lw needs to sign off.
Lines checked: 29, Warnings: 0, Errors: 1
Please
From: "grimlock.lw"
When Recving tcp stream form LOCAL port, and flows have a dp_hash group, linux
call skb_set_hash_from_sk to set skb->hash and skb->l4_hash, ovs use skb->hash
to select group bucket.
When tcp retransmission occurs,linux call sk_rethink_txhash to rehash skb->hash
of retransmi
Bleep bloop. Greetings grimlock.lw, 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: Author grimlock.lw needs to sign off.
WARNING: Unexpected sign-offs from developers who
When Recving tcp stream form LOCAL port, and flows have a dp_hash group, linux
call skb_set_hash_from_sk to set skb->hash and skb->l4_hash, ovs use skb->hash
to select group bucket.
When tcp retransmission occurs,linux call sk_rethink_txhash to rehash skb->hash
of retransmission packet, so the r
Hi Eelco,
> > - Could not find DPDK library in default search path, update
> > + Failed to link with DPDK, check config.log for more details.
> > + Could not find working DPDK library in default search path,
> > + update
> >PKG_CONFIG_PATH for pkg-config to
46 matches
Mail list logo