Re: [ovs-dev] [PATCH ovn v7 7/9] ovn-controller: Handle runtime data changes in flow output engine

On Sun, May 24, 2020 at 11:12 AM Han Zhou wrote: > On Sat, May 23, 2020 at 3:26 AM Numan Siddique wrote: > > > > > > > > On Thu, May 21, 2020 at 12:28 PM Han Zhou wrote: > >> > >> Please see my comments below. > >> > >> On Wed, May 20, 2020 at 12:41 PM wrote: > >> > > >> > From: Numan

Re: [ovs-dev] [PATCH ovn] Support packet metadata marking for logical port traffic.

On 5/1/20 8:48 PM, num...@ovn.org wrote: > From: Numan Siddique > > This patch adds a new column 'mark' in the Logical_Switch_Port > table in the NB DB. CMS can set a desired value in this column > and whenever a packet is received from the VIF of the logical port, > the NXM_NX_PKT_MARK field is

Re: [ovs-dev] [PATCH ovn v7 8/9] ovn-controller: Use the tracked runtime data changes for flow calculation.

On Thu, May 21, 2020 at 12:42 PM Han Zhou wrote: > On Wed, May 20, 2020 at 12:40 PM wrote: > > > > From: Venkata Anil > > > > This patch processes the logical flows of tracked datapaths > > and tracked logical ports. To handle the tracked logical port > > changes, reference of logical flows to

[ovs-dev] [PATCH ovn v8 2/8] ovn-controller: I-P for SB port binding and OVS interface in runtime_data.

From: Numan Siddique This patch handles SB port binding changes and OVS interface changes incrementally in the runtime_data stage which otherwise would have resulted in calls to binding_run(). Prior to this patch, port binding changes were handled differently. The changes were only evaluated to

[ovs-dev] [PATCH ovn v8 6/8] ovn-controller: Handle runtime data changes in flow output engine

From: Numan Siddique In order to handle runtime data changes incrementally, the flow outut runtime data handle should know the changed runtime data. Runtime data now tracks the changed data for any OVS interface and SB port binding changes. The tracked data contains a hmap of tracked datapaths

[ovs-dev] [PATCH ovn v8 5/8] ovn-controller: I-P for ct zone and OVS interface changes in flow output stage.

From: Numan Siddique This patch handles ct zone changes and OVS interface changes incrementally in the flow output stage. Any changes to ct zone can be handled by running physical_run() instead of running flow_output_run(). And any changes to OVS interfaces can be either handled incrementally

[ovs-dev] [PATCH ovn v8 1/8] ovn-controller: Store the local port bindings in the runtime data I-P state.

From: Numan Siddique This patch adds a new data structure - 'struct local_binding' which represents a probable local port binding. A new object of this structure is creared for each interface present in the integration bridge (br-int) with the external_ids:iface-id set. This struct has 2 main

[ovs-dev] [PATCH ovn v8 3/8] ovn-controller: I-P for datapath binding

From: Numan Siddique This patch adds partial support of incremental processing of datapath binding. If a datapath is deleted, then a full recompute is triggered if that datapath is present in the 'local_datapaths' hmap of runtime data. Acked-by: Mark Michelson Acked-by: Han Zhou

[ovs-dev] [PATCH ovn v8 4/8] I-P engine: Provide the option for an engine to store changed data

From: Numan Siddique With this patch, an engine node which is an input to another engine node can provide the tracked data. The parent of this engine node can handle this tracked data incrementally. At the end of the engine_run(), the tracked data of the nodes are cleared. Acked-by: Mark

Re: [ovs-dev] [PATCH ovn v7 5/9] ovn-controller: I-P for ct zone and OVS interface changes in flow output stage.

On Tue, May 26, 2020 at 8:05 AM Han Zhou wrote: > On Mon, May 25, 2020 at 8:02 AM Numan Siddique wrote: > > > > > > > > On Sun, May 24, 2020 at 11:32 AM Han Zhou wrote: > >> > >> On Sat, May 23, 2020 at 11:37 AM Numan Siddique wrote: > >> > > >> > > >> > > >> > On Sat, May 23, 2020 at 7:30 AM

Re: [ovs-dev] [RFC v2 PATCH 3/5] dpif-netdev: Support partial-action-offload of VXLAN encap flow

On 5/18/2020 10:27 PM, Sriharsha Basavapatna wrote: In this patch, we support offloading of VXLAN_ENCAP action for a vhost-user port (aka "partial-action-offload"). At the time of offloading the flow, we determine if the flow can be offloaded to an egress device, if the input port is not

Re: [ovs-dev] [PATCH ovn 2/2] northd: manage ARP request locally for FIP traffic

> On 5/26/20 5:23 AM, Han Zhou wrote: > > > > > > On Mon, May 25, 2020 at 2:55 PM Lorenzo Bianconi > > mailto:lorenzo.bianc...@redhat.com>> wrote: > >> > >> Introduce 150-priority logical flows for each NAT rule that can > >> be handled in a distributed manner to manage ARP request locally > >>

[ovs-dev] [PATCH ovn v8 0/8] Incremental processing improvements.

From: Numan Siddique This patch series handles port binding, datapath binding, ovs interface changes, runtime data changes, sb chassis changes incrementally. (These patches can also be found here - https://github.com/numansiddique/ovn/tree/IP_improvements_v5) Below are the results of some

Re: [ovs-dev] [PATCH ovn] Support packet metadata marking for logical port traffic.

On Tue, May 26, 2020 at 7:06 PM Dumitru Ceara wrote: > On 5/1/20 8:48 PM, num...@ovn.org wrote: > > From: Numan Siddique > > > > This patch adds a new column 'mark' in the Logical_Switch_Port > > table in the NB DB. CMS can set a desired value in this column > > and whenever a packet is

Re: [ovs-dev] [PATCH ovn 2/2] northd: manage ARP request locally for FIP traffic

> On Mon, May 25, 2020 at 2:55 PM Lorenzo Bianconi < > lorenzo.bianc...@redhat.com> wrote: > > > > Introduce 150-priority logical flows for each NAT rule that can > > be handled in a distributed manner to manage ARP request locally > > for FIP traffic. In particular set reg1 and eth.src to NAT

Re: [ovs-dev] [PATCH 01/11] netdev-offload-dpdk: Remove pre-validate of patterns function

On 5/19/2020 5:26 PM, Eli Britstein wrote: On 5/19/2020 4:41 PM, Sriharsha Basavapatna wrote: On Mon, May 18, 2020 at 9:10 PM Eli Britstein wrote: The function of adding patterns by requested matches checks that it consumed all the required matches, and err if not. This nullify the purpose

Re: [ovs-dev] [PATCH ovn v7 2/9] ovn-controller: I-P for SB port binding and OVS interface in runtime_data.

On Sat, May 23, 2020 at 6:42 AM Han Zhou wrote: > On Fri, May 22, 2020 at 3:07 PM Numan Siddique wrote: > > > > > > > > On Sat, May 23, 2020 at 3:10 AM Han Zhou wrote: > >> > >> On Fri, May 22, 2020 at 1:51 AM Numan Siddique wrote: > >> > > >> > > >> > > >> > On Fri, May 22, 2020 at 1:17 AM

Re: [ovs-dev] [PATCH ovn v7 4/9] ofctrl: Replace the actions of an existing flow if actions have changed.

On Thu, May 21, 2020 at 11:14 AM Han Zhou wrote: > Hi Numan, I think this patch is not harmful, but not necessary for the I-P > series. And for (2) in the commit message I want to clarify. Please see my > comments below. > You're right. This patch is not needed. It was earlier needed when the

Re: [ovs-dev] [RFC v2 PATCH 4/5] dpif-netdev: Skip encap action during datapath execution

On 5/18/2020 10:27 PM, Sriharsha Basavapatna wrote: In this patch we check if action processing (apart from OUTPUT action), should be skipped for a given dp_netdev_flow. Specifically, we check if the action is TNL_PUSH and if it has been offloaded to HW, then we do not push the tunnel header

Re: [ovs-dev] [PATCH ovn v7 2/9] ovn-controller: I-P for SB port binding and OVS interface in runtime_data.

* SNIPPED * What you described is correct (I believe). However, it is the declarative way of thinking, which is perfect for the always recompute implementation, but it is hard to reason the correctness and to maintain in longer term for incremental processing. Incremental processing focuses

Re: [ovs-dev] [PATCH v4] AB bonding: Add "primary" interface concept

On Thu, May 21, 2020 at 05:56:27PM +, Jeff Squyres (jsquyres) wrote: > On May 13, 2020, at 11:07 AM, Flavio Leitner wrote: > > I wonder if we could store a bond_slave pointer into struct bond > > instead of a string, because then we don't need the bool on each > > bond_slave to indicate if

[ovs-dev] [PATCH ovn v8 7/8] ovn-controller: Use the tracked runtime data changes for flow calculation.

From: Venkata Anil This patch processes the logical flows of tracked datapaths and tracked logical ports. To handle the tracked logical port changes, reference of logical flows to port bindings is maintained. Acked-by: Mark Michelson Co-Authored-by: Numan Siddique Signed-off-by: Venkata Anil

[ovs-dev] [PATCH ovn v8 8/8] ovn-controller: Handle sbrec_chassis changes incrementally.

From: Numan Siddique When ovn-controller updates the nb_cfg column of its chassis, this results in full recomputation on all the nodes. This results in wastage of CPU cycles. To address this, this patch handles sbrec_chassis changes incrementally. We don't need to handle any sbrec_chassis

Re: [ovs-dev] [PATCH] compat: Backport ipv6_stub change

On Mon, May 25, 2020 at 10:50 AM Ilya Maximets wrote: > > On 5/25/20 7:01 PM, Ilya Maximets wrote: > > On 5/24/20 7:59 PM, William Tu wrote: > >> On Thu, May 21, 2020 at 02:54:03PM -0700, Greg Rose wrote: > >>> A patch backported to the Linux stable 4.14 tree and present in the > >>> latest

Re: [ovs-dev] [RFC v2 PATCH 1/5] dpif-netdev: Refactor dp_netdev_flow_offload_put()

On 5/18/2020 10:27 PM, Sriharsha Basavapatna wrote: This patch refactors dp_netdev_flow_offload_put() to prepare for more changes to support partial action offload, in subsequent patches. - Add a wrapper function to allocate flow-mark. - Move netdev_ports_get() to before flow-mark allocation.

Re: [ovs-dev] [PATCH v2 5/5] dpif-lookup: add avx512 gather implementation

> -Original Message- > From: William Tu > Sent: Thursday, May 21, 2020 11:30 PM > To: Van Haaren, Harry > Cc: ovs-dev@openvswitch.org; i.maxim...@ovn.org > Subject: Re: [ovs-dev] [PATCH v2 5/5] dpif-lookup: add avx512 gather > implementation > > > > ovs-vsctl -- add-br br0 -- set Bridge

Re: [ovs-dev] [PATCH ovn 2/2] northd: manage ARP request locally for FIP traffic

On 5/26/20 5:39 PM, Lorenzo Bianconi wrote: >> On 5/26/20 5:23 AM, Han Zhou wrote: >>> >>> >>> On Mon, May 25, 2020 at 2:55 PM Lorenzo Bianconi >>> mailto:lorenzo.bianc...@redhat.com>> wrote: Introduce 150-priority logical flows for each NAT rule that can be handled in a distributed

[ovs-dev] MAY YOU BE BLESSED DEAR

-- GREETINGS: Dear Sir/Madam: may the peace of God be onto you I am (MRS: Shenzhen Liu) from Wuhan In China. However I know this message may come to you as a surprise, please consider this with all seriousness I solicited your assistance in the most polite language. I went through your Google

Re: [ovs-dev] [PATCH] datapath: Add hash info to upcall.

On Mon, May 25, 2020 at 8:40 AM Ilya Maximets wrote: > > On 5/24/20 8:41 PM, Han Zhou wrote: > > > > > > On Thu, May 7, 2020 at 11:21 PM Tonghao Zhang mailto:xiangxia.m@gmail.com>> wrote: > >> > >> On Mon, May 4, 2020 at 9:02 AM Han Zhou > wrote: > >> > > >> > This patch backports below

Re: [ovs-dev] [PATCH] ovs-ctl: Don't overwrite external-id hostname

On Mon, May 25, 2020 at 8:28 AM Daniel Alvarez wrote: > > ovs-ctl started to add the hostname as external-id [0] at some point. > > However, this can be problematic as if it's already set by an external > entity it will get overwritten. In RHEL systems, systemd will invoke > ovs-ctl to start OVS

Re: [ovs-dev] [PATCH v2] datapath: Add hash info to upcall.

Bleep bloop. Greetings Han Zhou, 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 Tonghao Zhang needs to sign off. WARNING: Unexpected sign-offs from developers who

[ovs-dev] [PATCH v2] datapath: Add hash info to upcall.

This patch backports below upstream patches, and add __skb_set_hash to compat for older kernels. commit b5ab1f1be6180a2e975eede18731804b5164a05d Author: Jakub Kicinski Date: Mon Mar 2 21:05:18 2020 -0800 openvswitch: add missing attribute validation for hash Add missing attribute

Re: [ovs-dev] [PATCH ovn 2/2] northd: manage ARP request locally for FIP traffic

On 5/26/20 5:23 AM, Han Zhou wrote: > > > On Mon, May 25, 2020 at 2:55 PM Lorenzo Bianconi > mailto:lorenzo.bianc...@redhat.com>> wrote: >> >> Introduce 150-priority logical flows for each NAT rule that can >> be handled in a distributed manner to manage ARP request locally >> for FIP traffic.

Re: [ovs-dev] [PATCH] ovsdb-server: Fix schema leak while reading db.

On Fri, May 15, 2020 at 9:25 AM Ilya Maximets wrote: > > parse_txn() function doesn't always take ownership of the 'schema' > passed. So, if the schema of the clustered db has same version as the > one that already in use, parse_txn() will not use it, resulting with a > memory leak: > > 7,827

Re: [ovs-dev] [PATCH ovn v7 8/9] ovn-controller: Use the tracked runtime data changes for flow calculation.

On Tue, May 26, 2020 at 6:57 AM Numan Siddique wrote: > > > > On Thu, May 21, 2020 at 12:42 PM Han Zhou wrote: >> >> On Wed, May 20, 2020 at 12:40 PM wrote: >> > >> > From: Venkata Anil >> > >> > This patch processes the logical flows of tracked datapaths >> > and tracked logical ports. To

Re: [ovs-dev] [PATCH ovn v3] ovn-controller to no longer monitor Chassis' external_ids

On Thu, May 14, 2020 at 12:52 AM Dumitru Ceara wrote: > > On 5/13/20 12:49 PM, lmart...@redhat.com wrote: > > From: Lucas Alvares Gomes > > > > Prior to this patch, the external_ids column from the Chassis table were > > being used for two purposes: > > > > 1. Holding configuration for the OVN

Re: [ovs-dev] [PATCH v5 1/3] ovsdb-server.7: Mention update3 as replies to monitor_cond_change.

On Thu, May 7, 2020 at 4:20 AM Dumitru Ceara wrote: > > Monitor_cond_change might trigger updates to be sent to clients as results > to condition changes. These updates can be either update2 (for monitor_cond > monitors) or update3 (for monitor_cond_since monitors). The documentation > used to

Re: [ovs-dev] [PATCH ovn 2/2] northd: manage ARP request locally for FIP traffic

On Tue, May 26, 2020 at 9:16 PM Dumitru Ceara wrote: > On 5/26/20 5:39 PM, Lorenzo Bianconi wrote: > >> On 5/26/20 5:23 AM, Han Zhou wrote: > >>> > >>> > >>> On Mon, May 25, 2020 at 2:55 PM Lorenzo Bianconi > >>> mailto:lorenzo.bianc...@redhat.com>> > wrote: > > Introduce 150-priority

Re: [ovs-dev] [PATCH 01/11] netdev-offload-dpdk: Remove pre-validate of patterns function

On 5/26/20 3:46 PM, Eli Britstein wrote: > > On 5/19/2020 5:26 PM, Eli Britstein wrote: >> >> On 5/19/2020 4:41 PM, Sriharsha Basavapatna wrote: >>> On Mon, May 18, 2020 at 9:10 PM Eli Britstein wrote: The function of adding patterns by requested matches checks that it consumed all the

Re: [ovs-dev] [PATCH] raft: Avoid sending equal snapshots.

On Tue, May 26, 2020 at 10:50 AM Ilya Maximets wrote: > > On 5/26/20 1:54 AM, Han Zhou wrote: > > > > > > On Mon, May 25, 2020 at 6:11 AM Ilya Maximets mailto:i.maxim...@ovn.org>> wrote: > >> > >> On 5/23/20 8:36 PM, Han Zhou wrote: > >> > > >> > > >> > On Sat, May 23, 2020 at 10:34 AM Ilya

Re: [ovs-dev] [PATCH] ovsdb: Add raft memory usage to memory report.

On 5/22/20 10:36 PM, Han Zhou wrote: > > > On Fri, May 22, 2020 at 10:36 AM Ilya Maximets > wrote: >> >> Memory reports could be found in logs or by calling 'memory/show' >> appctl command.  For ovsdb-server it includes information about db >> cells, monitor

Re: [ovs-dev] OVN static allocation reserved ranges

On Tue, May 26, 2020 at 1:18 PM Ben Pfaff wrote: > > Hi Han! > > I'm working on the port of ovn-northd to DDlog. It works, and now we're > working on optimizations. One of the areas where the DDlog > implementation has performance limitations is around ID allocation for > datapaths and ports,

Re: [ovs-dev] OVN static allocation reserved ranges

On Tue, May 26, 2020 at 01:51:54PM -0700, Han Zhou wrote: > On Tue, May 26, 2020 at 1:18 PM Ben Pfaff wrote: > > > > Hi Han! > > > > I'm working on the port of ovn-northd to DDlog. It works, and now we're > > working on optimizations. One of the areas where the DDlog > > implementation has

Re: [ovs-dev] [PATCH v2 ovn] northd: manage ARP request locally for FIP traffic

On Tue, May 26, 2020 at 9:47 AM Lorenzo Bianconi < lorenzo.bianc...@redhat.com> wrote: > > Modify 100-priority logical flows in Gateway Redirect table of > logical router ingress pipeline (table 15) in order to manage ARP > request locally for FIP traffic. In particular set reg1 and eth.src > to

[ovs-dev] OVN static allocation reserved ranges

Hi Han! I'm working on the port of ovn-northd to DDlog. It works, and now we're working on optimizations. One of the areas where the DDlog implementation has performance limitations is around ID allocation for datapaths and ports, so Leonid is working on a new allocator. OVN supports static

Re: [ovs-dev] [PATCH ovn 3/4] Prepare for 20.06.0

On Tue, May 26, 2020 at 11:33 PM Mark Michelson wrote: > Just so it's clear, I had wanted to get Numan's I-P improvements merged > before creating the 20.06 branch. > > I talked it over with him today and we agreed that we could get the > branch created now and then get the change merged to both

[ovs-dev] [PATCH v2 ovn] northd: manage ARP request locally for FIP traffic

Modify 100-priority logical flows in Gateway Redirect table of logical router ingress pipeline (table 15) in order to manage ARP request locally for FIP traffic. In particular set reg1 and eth.src to NAT external ip and NAT external mac respectively and do not distribute ARP traffic using FIP

[ovs-dev] Proposal

Hi,   Would you like to connect with key decision makers from the below sectors;   Manufacturing, Construction, Education, Retail, Healthcare, Energy, Utilities & Waste Treatment, Transportation, Banking & Finance, Media & Internet, Hospitality, etc.   You can contact them via direct 

[ovs-dev] [PATCH ovn 3/4] Prepare for 20.06.0

Signed-off-by: Mark Michelson --- NEWS | 2 +- configure.ac | 2 +- debian/changelog | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/NEWS b/NEWS index 083b929d4..d21a8ac16 100644 --- a/NEWS +++ b/NEWS @@ -1,4 +1,4 @@ -Post-v20.03.0 +OVN v20.06.0

[ovs-dev] [PATCH ovn 2/4] Move NEWS items credited to 20.03 to post-20.03

Signed-off-by: Mark Michelson --- NEWS | 20 +--- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/NEWS b/NEWS index a3c9b5448..083b929d4 100644 --- a/NEWS +++ b/NEWS @@ -1,17 +1,6 @@ Post-v20.03.0 -- - Added support for

[ovs-dev] [PATCH ovn 4/4] Prepare for post-20.06.0(20.06.90)

Signed-off-by: Mark Michelson --- NEWS | 3 +++ configure.ac | 2 +- debian/changelog | 6 ++ 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/NEWS b/NEWS index d21a8ac16..5d1d4dca2 100644 --- a/NEWS +++ b/NEWS @@ -1,3 +1,6 @@ +Post-v20.06.0

[ovs-dev] [PATCH ovn 1/4] Correct release date of OVN 20.03.0 in NEWS

Signed-off-by: Mark Michelson --- NEWS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/NEWS b/NEWS index 4dab4f7d5..a3c9b5448 100644 --- a/NEWS +++ b/NEWS @@ -3,7 +3,7 @@ Post-v20.03.0 - Added support for external_port_range in NAT table. -OVN v20.03.0 - xx xxx

Re: [ovs-dev] [PATCH ovn 3/4] Prepare for 20.06.0

Just so it's clear, I had wanted to get Numan's I-P improvements merged before creating the 20.06 branch. I talked it over with him today and we agreed that we could get the branch created now and then get the change merged to both master and branch-20.06 once they're ready. This way, we

Re: [ovs-dev] [PATCH ovn v8 8/8] ovn-controller: Handle sbrec_chassis changes incrementally.

On Tue, May 26, 2020 at 5:59 PM wrote: > From: Numan Siddique > > When ovn-controller updates the nb_cfg column of its chassis, > this results in full recomputation on all the nodes. This results > in wastage of CPU cycles. To address this, this patch handles > sbrec_chassis changes

Re: [ovs-dev] [PATCH v3 RESEND] classifier: Prevent tries vs n_tries race leading to NULL dereference.

On 5/18/20 1:06 AM, Eiichi Tsukata wrote: > Currently classifier tries and n_tries can be updated not atomically, > there is a race condition which can lead to NULL dereference. > The race can happen when main thread updates a classifier tries and > n_tries in classifier_set_prefix_fields() and at

[ovs-dev] OVN point releases

Hi everyone, In preparing for 20.06 today, I noticed we've never made a 20.03.1 release. The branch has a lot of useful bug fixes in it, and I think it would be good to release 20.03.1 soon. Does anybody disagree? Moving forward, I think that having some sort of documented process for

Re: [ovs-dev] [PATCH] raft: Avoid sending equal snapshots.

On 5/26/20 1:54 AM, Han Zhou wrote: > > > On Mon, May 25, 2020 at 6:11 AM Ilya Maximets > wrote: >> >> On 5/23/20 8:36 PM, Han Zhou wrote: >> > >> > >> > On Sat, May 23, 2020 at 10:34 AM Ilya Maximets > > > >

[ovs-dev] [PATCH v4] classifier: Prevent tries vs n_tries race leading to NULL dereference.

Currently classifier tries and n_tries can be updated not atomically, there is a race condition which can lead to NULL dereference. The race can happen when main thread updates a classifier tries and n_tries in classifier_set_prefix_fields() and at the same time revalidator or handler thread try

Re: [ovs-dev] [PATCH v5 2/3] ovsdb-idl: Avoid inconsistent IDL state with OVSDB_MONITOR_V3.

Thanks Dumitru. Please see my comments below. On Thu, May 7, 2020 at 4:21 AM Dumitru Ceara wrote: > > Assuming an ovsdb client connected to a database using OVSDB_MONITOR_V3 > (i.e., "monitor_cond_since" method) with the initial monitor condition > MC1. > > Assuming the following two

Re: [ovs-dev] [PATCH v3 RESEND] classifier: Prevent tries vs n_tries race leading to NULL dereference.

Hello Ilya Thanks for comments! Replied inline. > On May 27, 2020, at 1:28, Ilya Maximets wrote: > > On 5/18/20 1:06 AM, Eiichi Tsukata wrote: >> >> >> diff --git a/lib/classifier.c b/lib/classifier.c >> index 0fad953..10909a6 100644 >> --- a/lib/classifier.c >> +++ b/lib/classifier.c >> @@

Re: [ovs-dev] [PATCH v2 1/3] system-dpdk: cleanup stale hugepage files after tests

I tried --in-memory but finding issues with existing tests unable to pass mainly, being unable to ping between kernel veth and dpdk tap. Problem could be because of implicit --no-shconf ? .Can we handle this separately as it is blocking other patches ? Your opinions please. Regards. On Thu, May

Re: [ovs-dev] [PATCH 01/11] netdev-offload-dpdk: Remove pre-validate of patterns function

On 5/26/2020 11:30 PM, Ilya Maximets wrote: On 5/26/20 3:46 PM, Eli Britstein wrote: On 5/19/2020 5:26 PM, Eli Britstein wrote: On 5/19/2020 4:41 PM, Sriharsha Basavapatna wrote: On Mon, May 18, 2020 at 9:10 PM Eli Britstein wrote: The function of adding patterns by requested matches

Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Fix some cases all ethernet packets will be hw dropped.

On 4/18/2020 6:24 AM, JackerDune wrote: uplink-local (ip) <—> uplink <—> gw(gwip) When i use mlx5's vf and pf to offload my flow, i found my host vf ip can not get arp response of gw's ip, when i turn off offload, all works fine. I check ovs dpcls rules, find arp request flow is offloaded