Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

On 8/6/2020 8:28 PM, Stokes, Ian wrote: On 8/6/2020 6:17 PM, Emma Finn wrote: The following 2 commits introduced changes which caused a regression for XL710 devices and functionality ceases for partial offload as a result. 864852a0624a ("netdev-offload-dpdk: Fix Ethernet matching for type

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

Hi, There are still some connection errors from ovn-controller. Is that connection drop will cause flows to be deleted from vswitchd? .. 2020-08-07T03:55:22.269Z|03988|jsonrpc|WARN|tcp:127.0.0.1:6640: send error: Broken pipe ..

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

Interesting... with this configuration on gateway (chassis) node, external_ids: {ovn-bridge-mappings="physnet1:br-ex", ovn-cms-options=enable-chassis-as-gw, ovn-encap-ip="10.6.30.91", ovn-encap-type=geneve, ovn-openflow-probe-interval="30",

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

Hi Han and Numan, I'd like to have a few more clarifications. For inactivity probe: >From ovn-controller to ovn-sb-db: ovn-remote-probe-interval >From ovn-controller to ovs-vswitchd: ovn-openflow-probe-interval >From ovn-controller to local ovsdb: which interval? >From local ovsdb to

[ovs-dev] TNT Express delivery Consignment Notification

Dear Customer, A shipment has been arranged for you through TNT The shipment has been scheduled for delivery and has TNT consignment number: 87993766478. Attached is the documentation that relates to this Express Import Order Print and sign all copies of the consignment note. Note: For

Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

> -Original Message- > From: Stokes, Ian > Sent: Friday, August 7, 2020 1:29 AM > To: Eli Britstein ; Finn, Emma ; > d...@openvswitch.org; Xing, Beilei ; Guo, Jia > > Cc: i.maxim...@ovn.org > Subject: RE: [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching > HWOL for XL710

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

I think I have everything clarified here. I will make necessary tunes and rerun the test. Thanks! Tony > -Original Message- > From: Han Zhou > Sent: Thursday, August 6, 2020 12:42 PM > To: Tony Liu > Cc: Han Zhou ; Numan Siddique ; ovs-dev > ; ovs-discuss > Subject: Re:

[ovs-dev] Loan Offer

- This mail is in HTML. Some elements may be ommited in plain text. - Attention, Do you need Max Loan, Do you need a loan to clear your debts ? Are you going to increase your finances ? You are a business person who wants to expand his / her company. We give loan to individual and cooperate

Re: [ovs-dev] [PATCH v2] dpif-netlink: distribute polling to discreet handlers

Hi Aaron, Thanks for the patch. I ran some basic tests here and they passed. I could see only one handler thread becoming active with a single upcall. See my comment below. On Tue, Jul 21, 2020 at 07:27:41PM -0400, Aaron Conole wrote: > Currently, the channel handlers are polled globally. On

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

On Thu, Aug 6, 2020 at 12:07 PM Tony Liu wrote: > > Inline... > > Thanks! > > Tony > > -Original Message- > > From: Han Zhou > > Sent: Thursday, August 6, 2020 11:37 AM > > To: Tony Liu > > Cc: Han Zhou ; Numan Siddique ; ovs-dev > > ; ovs-discuss > > Subject: Re: [ovs-discuss] [OVN]

Re: [ovs-dev] [PATCH] meta-flow: fix a typo in "MPLS Bottom of Stack Field" paragraph

On 8/6/2020 9:33 AM, Timothy Redaelli wrote: In the ovs-fields.7 manual page, the "MPLS Bottom of Stack Field" paragraph says: * When mpls_bos is 1, there is another MPLS label following this one, so the Ethertype passed to pop_mpls should be an MPLS Ethertype. [...] * When mpls_bos

Re: [ovs-dev] [ovs-discuss] packet drop

Inline... Thanks! Tony > -Original Message- > From: Numan Siddique > Sent: Thursday, August 6, 2020 11:49 AM > To: Tony Liu > Cc: ovs-dev@openvswitch.org; ovs-disc...@openvswitch.org > Subject: Re: [ovs-discuss] [ovs-dev] packet drop > > On Fri, Aug 7, 2020 at 12:10 AM Tony Liu

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

Inline... Thanks! Tony > -Original Message- > From: Han Zhou > Sent: Thursday, August 6, 2020 11:37 AM > To: Tony Liu > Cc: Han Zhou ; Numan Siddique ; ovs-dev > ; ovs-discuss > Subject: Re: [ovs-discuss] [OVN] no response to inactivity probe > > > > On Thu, Aug 6, 2020 at 11:11 AM

[ovs-dev] [PATCH ovn v2] Allow force_snat options to work for dual-stack routers.

The lb_force_snat and dnat_force_snat options could accept only a single IP address. For routers that only route traffic of a single IP address family, this is fine. However, if a router routes both IPv4 and IPv6 traffic, then this limitation is a problem. This patch addresses this problem by

Re: [ovs-dev] [ovs-discuss] packet drop

On Fri, Aug 7, 2020 at 12:10 AM Tony Liu wrote: > > Inline... > > Thanks! > > Tony > > -Original Message- > > From: Numan Siddique > > Sent: Thursday, August 6, 2020 10:03 AM > > To: Tony Liu > > Cc: ovs-disc...@openvswitch.org; ovs-dev@openvswitch.org > > Subject: Re: [ovs-dev] packet

Re: [ovs-dev] [PATCH ovn v2 3/3] ovn-northd.c: Support optionally disabling neighbor learning from ARP request/NS.

On Thu, Aug 6, 2020 at 11:22 AM Numan Siddique wrote: > > On Thu, Aug 6, 2020 at 11:45 PM Han Zhou wrote: > > > > On Thu, Aug 6, 2020 at 11:07 AM Numan Siddique wrote: > > > > > > On Wed, Aug 5, 2020 at 12:36 PM Han Zhou wrote: > > > > > > > > Support a new logical router option

Re: [ovs-dev] [PATCH ovn] Allow force_snat options to work for dual-stack routers.

On Thu, Jul 16, 2020 at 11:37 PM Mark Michelson wrote: > > The lb_force_snat and dnat_force_snat options could accept only a single > IP address. For routers that only route traffic of a single IP address > family, this is fine. However, if a router routes both IPv4 and IPv6 > traffic, then this

Re: [ovs-dev] packet drop

Inline... Thanks! Tony > -Original Message- > From: Numan Siddique > Sent: Thursday, August 6, 2020 10:03 AM > To: Tony Liu > Cc: ovs-disc...@openvswitch.org; ovs-dev@openvswitch.org > Subject: Re: [ovs-dev] packet drop > > > > On Thu, Aug 6, 2020 at 4:05 AM Tony Liu

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

On Thu, Aug 6, 2020 at 11:11 AM Tony Liu wrote: > > Inline... (please read with monospaced font:)) > > Thanks! > > Tony > > -Original Message- > > From: Han Zhou > > Sent: Wednesday, August 5, 2020 11:48 PM > > To: Tony Liu > > Cc: Han Zhou ; Numan Siddique ; ovs-dev > > ; ovs-discuss

Re: [ovs-dev] [PATCH ovn v2 1/2] ovn-northd: Don't send the pkt to conntrack if it is to be routed in egress stage.

On 8/4/20 9:19 AM, num...@ovn.org wrote: > From: Numan Siddique > > If there is a logical port 'P1' with the IP - 10.0.0.3 and a logical port > 'P2' with > the IP 20.0.0.3 and if the logical switch of 'P1' has atleast one load > balancer > associated with it and atleast one ACL with

Re: [ovs-dev] [PATCH ovn v2 3/3] ovn-northd.c: Support optionally disabling neighbor learning from ARP request/NS.

On Thu, Aug 6, 2020 at 11:45 PM Han Zhou wrote: > > On Thu, Aug 6, 2020 at 11:07 AM Numan Siddique wrote: > > > > On Wed, Aug 5, 2020 at 12:36 PM Han Zhou wrote: > > > > > > Support a new logical router option "always_learn_from_arp_request" > that controls > > > behavior when handling ARP

Re: [ovs-dev] [PATCH ovn v2 3/3] ovn-northd.c: Support optionally disabling neighbor learning from ARP request/NS.

On Thu, Aug 6, 2020 at 11:07 AM Numan Siddique wrote: > > On Wed, Aug 5, 2020 at 12:36 PM Han Zhou wrote: > > > > Support a new logical router option "always_learn_from_arp_request" that controls > > behavior when handling ARP requests or IPv4 ND-NS packets. > > > > "true" - Always learn the

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

Inline... (please read with monospaced font:)) Thanks! Tony > -Original Message- > From: Han Zhou > Sent: Wednesday, August 5, 2020 11:48 PM > To: Tony Liu > Cc: Han Zhou ; Numan Siddique ; ovs-dev > ; ovs-discuss > Subject: Re: [ovs-discuss] [OVN] no response to inactivity probe > >

Re: [ovs-dev] [PATCH ovn v2 3/3] ovn-northd.c: Support optionally disabling neighbor learning from ARP request/NS.

On Wed, Aug 5, 2020 at 12:36 PM Han Zhou wrote: > > Support a new logical router option "always_learn_from_arp_request" that > controls > behavior when handling ARP requests or IPv4 ND-NS packets. > > "true" - Always learn the MAC/IP binding and add a new MAC_Binding entry > (default behavior) >

Re: [ovs-dev] [PATCH ovn v2 2/2] ovn-northd: Don't send the pkt to conntrack for NAT if its not destined for LB VIP.

On 8/4/20 9:19 AM, num...@ovn.org wrote: > From: Numan Siddique > > Presently when a logical switch has load balancer(s) associated to it, then > the > packet is still sent to conntrack with the action ct_lb on both the ingress > and egress logical switch pipeline even if the destination IP is

Re: [ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

On 8/6/20 1:47 PM, Numan Siddique wrote: On Thu, Aug 6, 2020 at 11:03 PM Mark Michelson wrote: On 8/6/20 12:16 PM, Numan Siddique wrote: On Thu, Aug 6, 2020 at 8:22 PM Mark Michelson mailto:mmich...@redhat.com>> wrote: In the fixes commit below, ct_commit was changed to use nested

Re: [ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

On Thu, Aug 6, 2020 at 11:03 PM Mark Michelson wrote: > > On 8/6/20 12:16 PM, Numan Siddique wrote: > > > > > > On Thu, Aug 6, 2020 at 8:22 PM Mark Michelson > > wrote: > > > > In the fixes commit below, ct_commit was changed to use nested actions. > > This

[ovs-dev] OVN Meeting Logs 06 August, 2020

Here is the IRC log for the OVN meeting for 06 August, 2020 http://eavesdrop.openstack.org/meetings//ovn_community_development_discussion/2020/ovn_community_development_discussion.2020-08-06-17.15.log.html If you are interested in attending this meeting, it happens every Thursday in the

Re: [ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

On 8/6/20 12:16 PM, Numan Siddique wrote: On Thu, Aug 6, 2020 at 8:22 PM Mark Michelson > wrote: In the fixes commit below, ct_commit was changed to use nested actions. This requires that curly braces be present for all ct_commits. When adjusting

Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

> On 8/6/2020 6:17 PM, Emma Finn wrote: > > The following 2 commits introduced changes which caused a regression > > for XL710 devices and functionality ceases for partial offload as a result. > > 864852a0624a ("netdev-offload-dpdk: Fix Ethernet matching for type > > only.") > > a79eae87abe4

[ovs-dev] CONTACT OUR INTERNATIONAL DIPLOMATIC AGENT, MR. JOHN BENDER TO RECEIVE YOUR ATM CARD WORTH $12.8MILLION US DOLLARS, This delivery was approved today, 06/08/2020

Attn,Dear. GOODNEWS FOR YOU. CONTACT OUR INTERNATIONAL DIPLOMATIC AGENT, MR. JOHN BENDER TO RECEIVE YOUR ATM CARD WORTH $12.8MILLION US DOLLARS, This delivery was approved today, 06/08/2020 Contact Person, AGENT, MR. JOHN BENDER Email: john.b...@yahoo.com Phone number (408) 650-6103, call or Text

[ovs-dev] [PATCH 1/1] dpdk: Deprecate vhost-user dequeue zero-copy.

Dequeue zero-copy is no longer supported for vhost-user client mode in DPDK due to commit [1]. In addition to this, zero-copy mode has been proposed to be marked deprecated in [2] with removal in the next DPDK LTS release. This commit deprecates support for vhost-user dequeue zero-copy in OVS

Re: [ovs-dev] packet drop

On Thu, Aug 6, 2020 at 4:05 AM Tony Liu wrote: > > The drop is caused by flow change. > > When packet is dropped. > >

[ovs-dev] [PATCH] meta-flow: fix a typo in "MPLS Bottom of Stack Field" paragraph

In the ovs-fields.7 manual page, the "MPLS Bottom of Stack Field" paragraph says: * When mpls_bos is 1, there is another MPLS label following this one, so the Ethertype passed to pop_mpls should be an MPLS Ethertype. [...] * When mpls_bos is 0, this MPLS label is the last one, so the

Re: [ovs-dev] [PATCH ovn] Add missing curly braces to bare ct_commits

Verified this fix on top of commit acd38429638c01afe1b2a1d15404e4724232ec1d . Tested-by: Flavio Fernandes > On Aug 6, 2020, at 9:38 AM, Mark Michelson wrote: > > In the fixes commit below, ct_commit was changed to use nested actions. > This requires that curly braces be present for all

Re: [ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

On Thu, Aug 6, 2020 at 8:22 PM Mark Michelson wrote: > In the fixes commit below, ct_commit was changed to use nested actions. > This requires that curly braces be present for all ct_commits. When > adjusting ovn-northd, some ct_commits were not updated to have them. > This commit changes the

Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

On 8/6/2020 6:17 PM, Emma Finn wrote: The following 2 commits introduced changes which caused a regression for XL710 devices and functionality ceases for partial offload as a result. 864852a0624a ("netdev-offload-dpdk: Fix Ethernet matching for type only.") a79eae87abe4 ("netdev-offload-dpdk:

Re: [ovs-dev] [PATCH v2] tc: Use skip_hw flag when probing tc features

On Tue, Aug 04, 2020 at 05:33:33PM +0800, Tonghao Zhang wrote: > On Tue, Aug 4, 2020 at 2:37 PM Roi Dayan wrote: > > > > There is no need to pass tc rules to hw when just probing > > for tc features. this will avoid redundant errors from hw drivers > > that may happen. > > > > Signed-off-by: Roi

[ovs-dev] [PATCH branch-2.13] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

The following commit introduced changes which caused a regression for XL710 devices and functionality ceases for partial offload as a result. 864852a0624a ("netdev-offload-dpdk: Fix Ethernet matching for type only.") Fixed by reversion of these changes. Signed-off-by: Emma Finn ---

[ovs-dev] [PATCH] netdev-offload-dpdk: Fix for broken ethernet matching HWOL for XL710 NIC

The following 2 commits introduced changes which caused a regression for XL710 devices and functionality ceases for partial offload as a result. 864852a0624a ("netdev-offload-dpdk: Fix Ethernet matching for type only.") a79eae87abe4 ("netdev-offload-dpdk: Remove pre-validate of patterns

Re: [ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

Bleep bloop. Greetings Mark Michelson, 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. git-am: error: sha1 information is lacking or useless (lib/actions.c). error: could not build fake

[ovs-dev] [PATCH v2] Allow bare ct_commits when no nested actions are required.

In the fixes commit below, ct_commit was changed to use nested actions. This requires that curly braces be present for all ct_commits. When adjusting ovn-northd, some ct_commits were not updated to have them. This commit changes the behavior of the ct_commit action not to require curly braces if

[ovs-dev] [PATCH ovn] Add missing curly braces to bare ct_commits

In the fixes commit below, ct_commit was changed to use nested actions. This requires that curly braces be present for all ct_commits. When adjusting ovn-northd, some ct_commits were not updated to have them. This commit fixes the issue. Fixes: 6cfb44a76c61("Used nested actions in ct_commit")

[ovs-dev] [PATCH ovn 2/2] pinctrl: Avoid flushing of non-local IGMP_Groups.

With ovn-monitor-all enabled, all ovn-controllers get updates about all SB records. This means that an ovn-controller might receive updates about IGMP_Groups inserted by other chassis on datapaths that are not local to the local chassis. These entries are valid and are not owned by the local

[ovs-dev] [PATCH ovn 0/2] Fix IGMP when ovn-monitor-all=true.

With ovn-monitor-all=true all chassis get updates about all SB DB records regardless if they're of interest to the local chassis or not. There's a bug in the IGMP code in ovn-controller which causes IGMP_Group records not owned by the local chassis to be flushed. The second patch in this series

[ovs-dev] [PATCH ovn 1/2] chassis: Propagate ovn-monitor-all external-id to Chassis:other_config.

At least for avoiding races in the unit tests it's useful to store the value of the OVS ovn-monitor-all external-id in the Chassis record other_config field. This allows us to know for sure when an ovn-controller has processed the update to the OVS Open_vSwitch DB table. Signed-off-by: Dumitru

[ovs-dev] Performance drop with conntrack flows

Hi, We see 40% traffic drop with UDP traffic over VxLAN and 20% traffic drop with UDP traffic over MPLSoGRE between OVS 2.8.2 & OVS 2.12.1. We narrowed the drop in performance in our test is due to below commit and backing out the commit fixed the performance drop problem. The commit of

Re: [ovs-dev] [ovs-discuss] [OVN] ovn-northd takes much CPU when no configuration update

On Tue, Aug 4, 2020 at 11:31 PM Han Zhou wrote: > On Tue, Aug 4, 2020 at 12:38 AM Numan Siddique wrote: > > > > > > > On Tue, Aug 4, 2020 at 9:02 AM Tony Liu wrote: > > > >> The probe awakes recomputing? > >> There is probe every 5 seconds. Without any connection up/down or > >> failover, > >>

Re: [ovs-dev] [PATCH ovn v2] Fix the routing for external logical ports of bridged logical switches.

Thanks Ankur for the lengthy reply. Please see below for some comments. Thanks Numan On Thu, Jul 30, 2020 at 9:23 AM Ankur Sharma wrote: > Hi Numan, Daniel, Lucas, > > Thank you so much for the feedback and providing your inputs. > I went the through the bug that was being referenced and

Re: [ovs-dev] [ovs-discuss] [OVN] no response to inactivity probe

On Wed, Aug 5, 2020 at 9:14 PM Tony Liu wrote: > I set the connection target="ptcp:6641:10.6.20.84" for ovn-nb-db > and "ptcp:6642:10.6.20.84" for ovn-sb-db. .84 is the first node > of cluster. Also ovn-openflow-probe-interval=30 on compute node. > It seems helping. Not that many