Add debug prints when creating and destroying rte flows, with all the
flow details (attributes, patterns, actions).
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/netdev-offload-dpdk.c | 209 ++
1 file changed, 138 insertions(+), 71
Populate dpif class field in offload struct to be used in offloading
flow put.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/dpif-netdev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 7ec217f39..80b3fdef3 100644
---
Flows that are offloaded via DPDK can be partially offloaded (matches
only) or fully offloaded (matches and actions). Set partially offloaded
display to (offloaded=partial, dp:ovs), and fully offloaded to
(offloaded=yes, dp:dpdk). Also support filter types "dpdk" and
"partially-offloaded".
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
Documentation/howto/dpdk.rst | 1 +
NEWS | 3 +-
lib/netdev-offload-dpdk.c| 99
3 files changed, 102 insertions(+), 1 deletion(-)
diff --git
Add a getter function for using the dpdk port id outside the scope of
netdev-dpdk.c to be used for HW offload.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/netdev-dpdk.c | 18 ++
lib/netdev-dpdk.h | 2 ++
2 files changed, 20 insertions(+)
diff --git
Signed-off-by: Eli Britstein
---
lib/netdev-offload-provider.h | 1 +
lib/netdev-offload.c | 12
2 files changed, 13 insertions(+)
diff --git a/lib/netdev-offload-provider.h b/lib/netdev-offload-provider.h
index 4e1c4251d..5a809c0cd 100644
---
Currently HW offload is accelerating only the rule matching sequence.
Introduce a framework for offloading rule actions as a pre-step for
processing the rule actions in HW. In case of a failure, fallback to the
legacy partial offload scheme.
Note: a flow will be fully offloaded only if it can
Implement the flow get method for DPDK, to get the statistics of the
provided ufid, towards reading statistics of fully offloaded flows.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/netdev-offload-dpdk.c | 47 +++
1 file changed, 47
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
Documentation/howto/dpdk.rst | 1 +
NEWS | 4 ++--
lib/netdev-offload-dpdk.c| 43 +++
3 files changed, 46 insertions(+), 2 deletions(-)
diff --git
Currently, netdev datapath offload only accelerates the flow match
sequence by associating a mark per flow. This series introduces the full
offload of netdev datapath flows by having the HW also perform the flow
actions.
This series adds HW offload for output, drop, set MAC, set IPv4 and set
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
Documentation/howto/dpdk.rst | 1 +
NEWS | 4 ++--
lib/netdev-offload-dpdk.c| 41 +
3 files changed, 44 insertions(+), 2 deletions(-)
diff --git
Refactor the flow patterns code to a helper function for better
readability and towards supporting more matches.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/netdev-offload-dpdk.c | 207 +-
1 file changed, 111 insertions(+), 96
Change the find method to return the whole entry of UFID-rte_flow
association instead of only the rte_flow field in it, as a pre-step
towards adding and using more fields into that map entry.
Signed-off-by: Eli Britstein
---
lib/netdev-offload-dpdk.c | 29 ++---
1 file
Action item data structures are pointed by rte_flow_action items.
Refactor the code to free the data structures when freeing the
rte_flow_action items, allowing simpler future actions simpler to add to
the code.
Signed-off-by: Eli Britstein
---
lib/netdev-offload-dpdk.c | 92
From: Ophir Munk
In case a flow is HW offloaded, packets do not reach the SW, thus not
counted for statistics. Use netdev flow get API in order to update the
statistics of flows by the HW statistics.
Co-authored-by: Eli Britstein
Signed-off-by: Ophir Munk
Reviewed-by: Oz Shlomo
Support offload of output action, also configuring count action for
allowing query statistics of HW offloaded flows.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
Documentation/howto/dpdk.rst | 17 ++---
NEWS | 1 +
lib/netdev-offload-dpdk.c| 86
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
Documentation/howto/dpdk.rst | 1 +
NEWS | 2 +-
lib/netdev-offload-dpdk.c| 4
3 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst
index
Introduce a rte flow query function as a pre-step towards reading HW
statistics of fully offloaded flows.
Signed-off-by: Eli Britstein
Reviewed-by: Oz Shlomo
---
lib/netdev-dpdk.c | 30 ++
lib/netdev-dpdk.h | 6 ++
2 files changed, 36 insertions(+)
diff --git
Instead of statically allocated pattern items on the stack, dynamically
allocate only the required items while parsing the matches, to simplify
the parsing and make it self-contained, without need of external types,
making it easier to support more matches in the future.
Signed-off-by: Eli
From: Tonghao Zhang
For installing more than MAX_FLOWS (65536) flows to netdev datapath.
Add the ovs-appctl subcommand "dpif-netdev/pmd-set-max-flow" which
can change the flow number which netdev datapath support.
Signed-off-by: Tonghao Zhang
---
v3:
* change the UINT_MAX to UINT32_MAX
* add
On Tue, Jan 7, 2020 at 3:55 AM Manoj Sharma wrote:
>
> A forwarding group is an aggregation of logical switch ports of a
> logical switch to load balance traffic across the ports. It also
> detects the liveness if the logical switch ports are realized as
> OVN tunnel ports on the physical
On Wed, Jan 8, 2020 at 7:02 AM wrote:
>
> From: Aliasgar Ginwala
>
> 1. Container scripts for starting ovn central node
>containers in HA using cluster mode
> 2. Update documentation about the same.
>
> Signed-off-by: Aliasgar Ginwala
Thanks. I applied this patch to master. I didn't test
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Attn:CEO
I have an investor looking to invest in entrepreneurial teams with big ideas
and a need for Seed Capital to turn their business or ideas into great
Companies.
He has funds available for Investment and want them invested under you or your
Company strict guidance. For more
Hi Ben,
After taking closer look at different driver implementations, I found
that the use of combined channels is actually driver dependent.
>From ethtool (8), a channel is an IRQ and the set of queues that can
trigger that IRQ. I tend to think channel as rx/tx queues from
software's point of
Hi Han,
If you have time, Could you review this patch or give a response.
Thanks ,
Yun
From: taoyunxi...@cmss.chinamobile.com
Date: 2019-12-24 19:55
To: Han Zhou
CC: ovs-dev
Subject: Re: Re: [ovs-dev] [PATCH ovn v4 0/2] Add a way to delete QoS directly
Hi Han,
Thanks for
Hi,
We have a requirement to update the datatype of a column in OVN-SB. However,
this is not straight-forward.
There could be existing entries in the database that has the old type and hence
the change will not be backward compatible.
Here is the reason for this requirement -
According
Der Betrag von 2.5000.000,00 wurde Ihnen von Frau Maureen David gespendet.
Bitte kontaktieren Sie sie per E-Mail: makaltschm...@gmail.com
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On Wed, Jan 08, 2020 at 02:51:09PM -0500, Lance Richardson via dev wrote:
> Update email address for Lance Richardson.
>
> Signed-off-by: Lance Richardson
Thanks, Lance. I applied this to master.
___
dev mailing list
d...@openvswitch.org
On Wed, Jan 08, 2020 at 10:48:04AM +0530, Vishal Deep Ajmera wrote:
> Problem:
>
> In OVS-DPDK, flows with output over a bond interface of type “balance-tcp”
> (using a hash on TCP/UDP 5-tuple) get translated by the ofproto layer into
> "HASH" and "RECIRC" datapath actions. After
Extend the existing infrastructure used for IPv4 multicast to
IPv6 multicast:
- snoop MLDv1 & MLDv2 reports.
- if multicast querier is configured, generate MLDv2 queries.
- support IPv6 multicast relay.
- support static flood configuration for IPv6 multicast too.
Signed-off-by: Dumitru Ceara
---
Signed-off-by: Dumitru Ceara
---
lib/logical-fields.c |3 ++-
northd/ovn-northd.c |2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/lib/logical-fields.c b/lib/logical-fields.c
index 8fb591c..5748b67 100644
--- a/lib/logical-fields.c
+++ b/lib/logical-fields.c
@@
The first patch of the series is a minor fix of how IP multicast traffic
is matched.
The second patch extends the already existing IPv4 Multicast support
(IGMP snooping, IGMP querier, relay and static flood config) to IPv6
by implementing MLDv1 & MLDv2 snooping and querier.
Signed-off-by:
Update email address for Lance Richardson.
Signed-off-by: Lance Richardson
---
.mailmap| 1 +
AUTHORS.rst | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/.mailmap b/.mailmap
index 4688ab0cd..894062d48 100644
--- a/.mailmap
+++ b/.mailmap
@@ -53,6 +53,7 @@ Joe Stringer
On 1/8/2020 7:54 PM, Hemal Shah wrote:
Ilya and Eli,
I have some additional comments on the v6 series.
1. The description says that tunnel push action is supported by this series
but v3-v4 note says that - dropped clone commit - will be posted in the next
series. In that case, should the
On Wed, Jan 08, 2020 at 05:32:48PM +0800, xiangxia.m@gmail.com wrote:
> From: Tonghao Zhang
>
> For installing more than MAX_FLOWS (65536) flows to netdev datapath.
> Add the ovs-appctl subcommand "dpif-netdev/pmd-set-max-flow" which
> can change the flow number which netdev datapath
On Wed, Jan 08, 2020 at 05:33:59PM +, Stokes, Ian wrote:
>
>
> On 1/8/2020 11:09 AM, Stokes, Ian wrote:
> > Hi Ben,
> >
> > just wanted to confirm if the soft freeze for OVS 2.13 is still
> > confirmed for January 15th? Just a had a few queries so thought it would
> > be best to ask.
>
>
On 1/8/2020 5:56 PM, Ilya Maximets wrote:
On 08.01.2020 18:37, Stokes, Ian wrote:
On 1/8/2020 4:38 PM, Ilya Maximets wrote:
On 07.01.2020 11:51, Stokes, Ian wrote:
On 1/2/2020 12:27 PM, Ilya Maximets wrote:
On 20.12.2019 16:28, Emma Finn wrote:
Add an ovs-appctl command to iterate
> On Fri, Dec 20, 2019 at 5:02 PM Lorenzo Bianconi
> wrote:
> >
> > Introduce IPv6 Prefix delegation state machine according to RFC 3633
> > https://tools.ietf.org/html/rfc3633.
> > Add handle_dhcpv6_reply controller action to parse advertise/reply from
> > IPv6 delegation server.
> > Introduce
On 08.01.2020 18:25, Eli Britstein wrote:
>
> On 1/8/2020 2:17 PM, Ilya Maximets wrote:
>> On 19.12.2019 12:54, Eli Britstein wrote:
>>> Flows that are offloaded via DPDK can be partially offloaded (matches
>>> only) or fully offloaded (matches and actions). Set partially offloaded
>>> display to
Ilya and Eli,
I have some additional comments on the v6 series.
1. The description says that tunnel push action is supported by this
series but v3-v4 note says that - dropped clone commit - will be posted in
the next series. In that case, should the description of patcheset be
On 08.01.2020 18:37, Stokes, Ian wrote:
>
>
> On 1/8/2020 4:38 PM, Ilya Maximets wrote:
>> On 07.01.2020 11:51, Stokes, Ian wrote:
>>>
>>>
>>> On 1/2/2020 12:27 PM, Ilya Maximets wrote:
On 20.12.2019 16:28, Emma Finn wrote:
> Add an ovs-appctl command to iterate through the dpcls
>
On 1/8/2020 12:57 AM, Simon Horman wrote:
On Tue, Jan 07, 2020 at 08:35:57AM -0800, Gregory Rose wrote:
On 1/7/2020 1:34 AM, Simon Horman wrote:
On Mon, Jan 06, 2020 at 01:36:34PM -0800, Greg Rose wrote:
...
--- a/datapath/linux/compat/ip6_gre.c
+++ b/datapath/linux/compat/ip6_gre.c
@@
On 1/8/2020 4:38 PM, Ilya Maximets wrote:
On 07.01.2020 11:51, Stokes, Ian wrote:
On 1/2/2020 12:27 PM, Ilya Maximets wrote:
On 20.12.2019 16:28, Emma Finn wrote:
Add an ovs-appctl command to iterate through the dpcls
and for each subtable output the miniflow bits for any
existing table.
On 1/8/2020 11:09 AM, Stokes, Ian wrote:
Hi Ben,
just wanted to confirm if the soft freeze for OVS 2.13 is still
confirmed for January 15th? Just a had a few queries so thought it would
be best to ask.
Apologies, was just pointed out to me on the community call, that soft
freeze was
On 1/8/2020 2:17 PM, Ilya Maximets wrote:
> On 19.12.2019 12:54, Eli Britstein wrote:
>> Flows that are offloaded via DPDK can be partially offloaded (matches
>> only) or fully offloaded (matches and actions). Set partially offloaded
>> display to (offloaded=partial, dp:ovs), and fully offloaded
On 07.01.2020 11:51, Stokes, Ian wrote:
>
>
> On 1/2/2020 12:27 PM, Ilya Maximets wrote:
>> On 20.12.2019 16:28, Emma Finn wrote:
>>> Add an ovs-appctl command to iterate through the dpcls
>>> and for each subtable output the miniflow bits for any
>>> existing table.
>>>
>>> $ ovs-appctl
David Ahern writes:
> On 12/16/19 2:42 PM, Aaron Conole wrote:
>> Can you try the following and see if your scalability issue is
>> addressed? I think it could be better integrated, but this is a
>> different quick 'n dirty.
>
> your patch reduces the number of threads awakened, but it is still
On 07.01.2020 20:19, Ben Pfaff wrote:
> On Sun, Dec 08, 2019 at 08:33:46PM +0100, Ilya Maximets wrote:
>> This pointer was introduced in July 2014 by commit
>> 6b31e07347ad ("dpif-netdev: Polling threads directly call ofproto upcall
>> functions.")
>> and it was broken right from this point
Timothy Redaelli writes:
> On DPDK 19.11 RTE_IBVERBS_LINK_DLOPEN is used by Mellanox PMDs (mlx4 and
> mlx5) instead of RTE_LIBRTE_MLX{4,5}_DLOPEN_DEPS.
>
> Without this commit is not possible to statically link OVS with DPDK when MLX4
> or MLX5 PMDs are enabled.
>
> Signed-off-by: Timothy
On Wed, Jan 8, 2020 at 1:42 PM Timothy Redaelli wrote:
> On DPDK 19.11 RTE_IBVERBS_LINK_DLOPEN is used by Mellanox PMDs (mlx4 and
> mlx5) instead of RTE_LIBRTE_MLX{4,5}_DLOPEN_DEPS.
>
> Without this commit is not possible to statically link OVS with DPDK when MLX4
> or MLX5 PMDs are enabled.
>
>
On 31.12.2019 21:14, Flavio Leitner wrote:
> Abbreviated as TSO, TCP Segmentation Offload is a feature which enables
> the network stack to delegate the TCP segmentation to the NIC reducing
> the per packet CPU overhead.
>
> A guest using vhost-user interface with TSO enabled can send TCP packets
On DPDK 19.11 RTE_IBVERBS_LINK_DLOPEN is used by Mellanox PMDs (mlx4 and
mlx5) instead of RTE_LIBRTE_MLX{4,5}_DLOPEN_DEPS.
Without this commit is not possible to statically link OVS with DPDK when MLX4
or MLX5 PMDs are enabled.
Signed-off-by: Timothy Redaelli
---
acinclude.m4 | 4 ++--
1 file
On 19.12.2019 12:54, Eli Britstein wrote:
> Flows that are offloaded via DPDK can be partially offloaded (matches
> only) or fully offloaded (matches and actions). Set partially offloaded
> display to (offloaded=partial, dp:ovs), and fully offloaded to
> (offloaded=yes, dp:dpdk). Also support
> -Original Message-
> From: Stokes, Ian
> Sent: Tuesday 7 January 2020 10:21
> To: Finn, Emma ; u9012...@gmail.com;
> i.maxim...@ovn.org; ovs-dev@openvswitch.org
> Subject: Re: [ovs-dev] [v1] dpif-netdev: Add ovs-appctl dpif-
> netdev/subtable-show.
>
>
>
> On 12/20/2019 3:28 PM,
On Wed, Jan 8, 2020 at 1:23 PM Han Zhou wrote:
>
> On Thu, Jan 2, 2020 at 11:51 AM Numan Siddique wrote:
> >
> > On Fri, Jan 3, 2020 at 1:00 AM Ben Pfaff wrote:
> > >
> > > On Fri, Jan 03, 2020 at 12:45:06AM +0530, Numan Siddique wrote:
> > > > Hi Ben,
> > > >
> > > > ovn-controller.c has the
On Tue, Jan 7, 2020 at 10:20 PM Lorenzo Bianconi
wrote:
>
> Changes since v1:
> - rely on xstrdup instead of ds_clone
>
> Lorenzo Bianconi (2):
> DNSSL: copy dnssl string in order to avoid truncated value
> RA Route Info Option: copy route info string in order to avoid
> truncated value
Hi Ilya,
I have a setup with vxlan, and then I do dp_hash (after pop).
First packet does pop in SW, so RSS is invalidated (and anyway it was probably
calculated on outer), dp_hash is calculated again SW.
Following packet will do decap in HW so packet has a valid internal RSS
(mark+rss),
And
Hi Ben,
just wanted to confirm if the soft freeze for OVS 2.13 is still
confirmed for January 15th? Just a had a few queries so thought it would
be best to ask.
Regards
Ian
___
dev mailing list
d...@openvswitch.org
On 1/7/2020 6:09 PM, Flavio Leitner wrote:
Hi Ian,
Thanks for the reviews. I agree with your comments for the other
patches. This one I will answer them inline.
Thanks Flavio,
below seems good to me, I know Ciara is testing this (and will test the
latest revsion also with a few
Hi,
There is an important use case for having OVS change MAC addresses of dpdk
interfaces.
OpenStack for example needs to update the MAC address of a VF assigned to a VM,
where the corresponding VF representor is owned by dpdk.
For some NIC vendors using "ifconfig" or "ip" commands - is not an
On Tue, Jan 07, 2020 at 06:13:32PM +0100, Ilya Maximets wrote:
> On 07.01.2020 18:08, Simon Horman wrote:
> > On Tue, Jan 07, 2020 at 10:34:37AM +0100, Simon Horman wrote:
> >> On Mon, Jan 06, 2020 at 01:36:34PM -0800, Greg Rose wrote:
> >>> A change backported to the Linux 4.14.162 LTS kernel
Bleep bloop. Greetings Tonghao Zhang, 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
WARNING: Line has trailing whitespace
#54
On Wed, Jan 8, 2020 at 6:34 AM Ben Pfaff wrote:
>
> On Mon, Dec 23, 2019 at 07:17:34PM +0800, xiangxia.m@gmail.com wrote:
> > From: Tonghao Zhang
> >
> > There may be too many flows (> MAX_FLOWS 65536) on
> > dpif-netdev at same time. For this case, we support
> > the ovs-appctl command to
From: Tonghao Zhang
For installing more than MAX_FLOWS (65536) flows to netdev datapath.
Add the ovs-appctl subcommand "dpif-netdev/pmd-set-max-flow" which
can change the flow number which netdev datapath support.
Signed-off-by: Tonghao Zhang
---
v2:
* change int type to atomic_uint32_t
*
On Tue, Jan 07, 2020 at 08:35:57AM -0800, Gregory Rose wrote:
> On 1/7/2020 1:34 AM, Simon Horman wrote:
> > On Mon, Jan 06, 2020 at 01:36:34PM -0800, Greg Rose wrote:
...
> > > --- a/datapath/linux/compat/ip6_gre.c
> > > +++ b/datapath/linux/compat/ip6_gre.c
> > > @@ -1089,7 +1089,11 @@ static
66 matches
Mail list logo