Re: [ovs-dev] gateway logic question (was: Re: [PATCH v2 1/5] ovsdb-idl: Redesign use of indexes.)

I think it may be a corner case, since in most cases we just need one gateway port per logical router. And for my understanding OpenStack doesn't have the API to set more than one gateway ports for a logical router, so at least it should be no issue in that set up. On Tue, Jun 12, 2018 at 9:39

Re: [ovs-dev] [PATCH] [RFC] ovn-controller: Experiment with restricting access to columns.

On Wed, Jun 13, 2018 at 3:37 PM, Ben Pfaff wrote: > > To make ovn-controller recompute incrementally, we need accurate > dependencies for each function that reads or writes a table. It's > currently difficult to be sure about these dependencies, and certainly > difficult to maintain them over

Re: [ovs-dev] [PATCH] vxlan: Fix for the packet loop issue in vxlan

On Wed, Jun 13, 2018 at 5:16 AM, Neelakantam Gaddam wrote: > It should be Qdisc's busylock in dev_queue_xmit function. I have seen the > issue in kernel version is 3.10.87 vanilla. > I see, This looks like general problem which exist in upstream kernel. You would be able to reproduce it even

[ovs-dev] [PATCH v9 0/7] OVS-DPDK flow offload with rte_flow

Hi Yuanhan/Finn/Shahaf, I tried hw-offloading patch on top OvS v2.9.0 and DPDK 17.11.0 with VXLAN encap/decap functionalities. VXLAN encap is working fine, however VXLAN decap functionality is broken, Please find HW/SW conf and Setup as below: [HW/SW configuration]: CPU:

[ovs-dev] Efectos de la Inflación

InnovaGroup Webinar Interactivo 19 y 20 de Junio "Actualización 2018 en las Normas de Información Financiera. " ¿Qué veré en este webinar? Las NIF (Normas de Información Financiera) comprenden un conjunto de conceptos generales y normas particulares que regulan la elaboración y

[ovs-dev] [PATCH] [RFC] ovn-controller: Experiment with restricting access to columns.

To make ovn-controller recompute incrementally, we need accurate dependencies for each function that reads or writes a table. It's currently difficult to be sure about these dependencies, and certainly difficult to maintain them over time, because there's no way to actually enforce them. This

[ovs-dev] [PATCH 1/2] lldp: fix string warnings

lib/lldp/lldpd.c: In function : lib/lldp/lldpd.c:520:17: warning: output truncated before terminating nul copying as many bytes from a string as its length [-Wstringop-truncation] strncat(buffer, cfg->g_protocols[i].name, ^

[ovs-dev] [PATCH 2/2] netdev-dpdk: fix snprintf call

lib/netdev-dpdk.c: In function : lib/netdev-dpdk.c:2865:49: warning: output may be truncated before the last format character [-Wformat-truncation=] snprintf(vhost_vring, 16, "vring_%d_size", i); ^ lib/netdev-dpdk.c:2865:9: note: output

Re: [ovs-dev] [PATCH] OVN: add ICMP time exceeded support to OVN logical router

Hi Lorenzo, the patch looks good to me. I have one comment on the test you added, though. See below. On 06/05/2018 11:57 AM, Lorenzo Bianconi wrote: Using icmp4 action, send an ICMP time exceeded frame whenever an OVN logical router receives an IPv4 packets whose TTL has expired (ip.ttl == {0,

Re: [ovs-dev] Issue with OVS 2.9.0, DPDK 18.02 and vhost-user

On 6/12/2018 9:50 PM, Ravi Kerur wrote: On Tue, Jun 12, 2018 at 3:31 AM, Stokes, Ian > wrote: > Hi, > > I have used first link to install, compile and run OVS 2.9.0 and DPDK > 18.02, second link to configure vhost-client ports. However, facing

Re: [ovs-dev] [PATCH] OVN python IDL: avoid useless JSON conversion to enhance performance

Thank you very much Ben :) On Wed, Jun 13, 2018 at 5:20 PM Ben Pfaff wrote: > OK, I crossported to branch-2.9. > > On Wed, Jun 13, 2018 at 01:24:44PM +0200, Miguel Angel Ajo Pelayo wrote: > > Ben, Russell, could we get this down to ovs 2.9? > > > > It's very important for scale. > > > > Best

Re: [ovs-dev] [PATCH] OVN python IDL: avoid useless JSON conversion to enhance performance

OK, I crossported to branch-2.9. On Wed, Jun 13, 2018 at 01:24:44PM +0200, Miguel Angel Ajo Pelayo wrote: > Ben, Russell, could we get this down to ovs 2.9? > > It's very important for scale. > > Best regards, > Miguel Ángel. > > On Wed, Jun 13, 2018 at 1:13 PM Daniel Alvarez Sanchez > wrote:

Re: [ovs-dev] [PATCH] vxlan: Fix for the packet loop issue in vxlan

It should be Qdisc's busylock in dev_queue_xmit function. I have seen the issue in kernel version is 3.10.87 vanilla. On Wed, Jun 13, 2018 at 12:21 PM, Pravin Shelar wrote: > On Tue, Jun 12, 2018 at 10:58 PM, Neelakantam Gaddam > wrote: > > Hi Pravin, > > > > I have seen the below crash. > >

Re: [ovs-dev] [PATCH] OVN python IDL: avoid useless JSON conversion to enhance performance

Ben, Russell, could we get this down to ovs 2.9? It's very important for scale. Best regards, Miguel Ángel. On Wed, Jun 13, 2018 at 1:13 PM Daniel Alvarez Sanchez wrote: > Hi, > Bringing this up again. > Can we please get this backported into 2.9 branch? The enhancement is very > noticeable.

Re: [ovs-dev] [PATCH] OVN python IDL: avoid useless JSON conversion to enhance performance

Hi, Bringing this up again. Can we please get this backported into 2.9 branch? The enhancement is very noticeable. Thanks a lot! Daniel On Tue, Mar 6, 2018 at 5:09 PM, Lucas Alvares Gomes wrote: > Hi, > > Excellent investigative work here Daniel, thanks for that! > > On Wed, Feb 28, 2018 at

Re: [ovs-dev] OVS DPDK: dpdk_merge pull request for master

> Thanks for the pull requests. I merged all of these (master, 2.9, and > 2.8). Thanks Ben. ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH] vxlan: Fix for the packet loop issue in vxlan

On Tue, Jun 12, 2018 at 10:58 PM, Neelakantam Gaddam wrote: > Hi Pravin, > > I have seen the below crash. > > [] show_stack+0x6c/0xf8 > > [] do_raw_spin_lock+0x168/0x170 > > [] dev_queue_xmit+0x43c/0x470 > > [] ip_finish_output+0x250/0x490 > > [] rpl_iptunnel_xmit+0x134/0x218 [openvswitch] > > []

Re: [ovs-dev] [PATCH v9 0/7] OVS-DPDK flow offload with rte_flow

Hi Flavio, I repeatedly tried to reproduce the results you have but failed. In fact I am now see better results for the hw-offload (thanks to optimization I learned from your script). w/o hw-offload I get fwd rate of ~7.76Mpps pmd thread numa_id 1 core_id 1: