Re: [ovs-dev] [PATCH ovn] Improve documentation of gateways.

Hi Ben, sorry for the late reply. I know it is merged, but I still want to share a few comments below. Maybe we can discuss and work on a follow-up patch if needed. On Thu, Mar 5, 2020 at 11:37 AM Ben Pfaff wrote: > > I found the documentation for gateways, especially HA gateways, to > be unclear

[ovs-dev] [PATCH] dpif-netlink: avoid netlink modify flow put op failed after tc modify flow put op failed.

From: wenxu The tc modify flow put always delete the original flow first and then add the new flow. If the modfiy flow put operation failed, the flow put operation will change from modify to create if success to delete the original flow in tc (which will be always failed with ENOENT, the flow is

[ovs-dev] [PATCH -next 000/491] treewide: use fallthrough;

es matched by all F: patterns in in each section. Done via the perl script below and the previously posted cvt_fallthrough.pl script. Link: https://lore.kernel.org/lkml/b56602fcf79f849e733e7b521bb0e17895d390fa.1582230379.git.joe.com/ These patches are based on next-20200310 and are available in gi

[ovs-dev] [PATCH OVN] Add external_ids column for tables in nb schema

"Logical_Router_Policy" and "Forwarding_Group" tables doesn't have "external_ids" column. I think it is better to add it, so CMS could fill it with useful information. Author: Tao YunXiang Co-authored-by: Liu Chang Co-authored-by: Rong Yin Signed-off-by: Tao YunXiang Signed-off-by: Liu C

Re: [ovs-dev] [PATCHv3 1/2] userspace: Enable TSO support for non-DPDK.

Hi William, Any chance to get the function comments copied to the non-dpdk versions as well? I wonder if we could define DP_PACKET_OL.* defines as it is proposed in this patch if DPDK is not enabled, or define them as DPDK defines. For example: #ifdef DPDK DP_PACKET_OL_TX_TCP_SEG = PKT_TX_

[ovs-dev] jsonrpc and unbounded amount of cpu

Hi, The input_buffer in struct jsonrpc was recently increased to 4k [ https://github.com/openvswitch/ovs/commit/ea5c1ba0e3b899b8b6684f23a44bbfd4331815ee ] Years ago there was a change [ https://github.com/openvswitch/ovs/commit/3a4548cfb2fb7e7344618f449ab9bf651ef83e6b ] to limit how much c

Re: [ovs-dev] [PATCH v6] Use TPACKET_V3 to accelerate veth for userspace datapath

On Fri, Mar 6, 2020 at 6:35 AM wrote: > > From: Yi Yang > > We can avoid high system call overhead by using TPACKET_V3 > and using DPDK-like poll to receive and send packets (Note: send > still needs to call sendto to trigger final packet transmission). > > From Linux kernel 3.10 on, TPACKET_V3 h

Re: [ovs-dev] [PATCH] ovsdb-idl.c: Clear conditions when clearing IDL.

On 3/5/20 9:50 PM, Ben Pfaff wrote: > On Tue, Mar 03, 2020 at 01:47:48PM +0100, Dumitru Ceara wrote: >> CC-ing Andy and Ben. >> >> On 3/3/20 7:43 AM, Han Zhou wrote: >>> >>> >>> On Mon, Mar 2, 2020 at 7:55 AM Dumitru Ceara >> > wrote: On 2/29/20 12:00 AM, Dumitru

[ovs-dev] [PATCH v2] ovsdb-idl.c: Clear conditions when clearing IDL.

If the ovsdb-server reply to "monitor_cond_since" requests has "found" == false then ovsdb_idl_db_parse_monitor_reply() calls ovsdb_idl_db_clear() which iterates through all tables and unconditionally sets table->cond_changed to false. However, if the client had already set a new condition for som

Re: [ovs-dev] [PATCH v2 ovn] logical-fields: fix memory leak caused by initialize ovnfield_by_name twice

thanks for sharing your information with me. Obviously I didn't understand you well. thanks, damijan On Tue, 10 Mar 2020, 16:51 Numan Siddique, wrote: > On Tue, Mar 10, 2020 at 7:10 PM Damijan Skvarc > wrote: > > > > On Tue, Mar 10, 2020 at 2:02 PM Numan Siddique wrote: > > > > > On Sat, Mar 7

Re: [ovs-dev] [PATCH v2 ovn] logical-fields: fix memory leak caused by initialize ovnfield_by_name twice

On Tue, Mar 10, 2020 at 7:10 PM Damijan Skvarc wrote: > > On Tue, Mar 10, 2020 at 2:02 PM Numan Siddique wrote: > > > On Sat, Mar 7, 2020 at 4:42 AM Ben Pfaff wrote: > > > > > > On Thu, Mar 05, 2020 at 07:21:41AM +0100, Damijan Skvarc wrote: > > > > ovnfield_by_name is hash of strings which is u

[ovs-dev] [RFC PATCH 5/5] bpf: Add reference XDP program implementation for netdev-offload-xdp

Currently only supports very basic keys and output action. We cannot support many keys/actions at the same time because the BPF verifier has 1M insn limitation. So the plan is to add config options to skip compilation for keys/actions as well as adding more keys/actions. Users of this reference pr

[ovs-dev] [RFC PATCH 4/5] tun_metadata: Use OVS_ALIGNED_VAR to align opts field

In the following commit I want to include flow.h from BPF programs, but with "clang -target bpf" with clang 9, UINTPTR_MAX somehow equals to UINT32_MAX while the size of pointer is 8. As a result unnecessary pad is added in struct tun_metadata in bpf code and cannot build bpf code due to build asse

[ovs-dev] [RFC PATCH 3/5] netdev-offload: Register xdp flow api provider

*** THIS PATCH IS NOT INTENDED TO BE APPLIED *** Temporarily comment out TC flow api provider for testing and register xdp offload provider. FIXME: Need a way to specify flow api provider from configuration. Signed-off-by: Toshiaki Makita --- lib/netdev-afxdp.c| 3 ++- lib/netdev-o

[ovs-dev] [RFC PATCH 2/5] netdev-offload: Add xdp flow api provider

This provider offloads classifier to software XDP (not hardware at this point). It works only when a custom XDP object is loaded by afxdp netdev. When the custom object meets certain requirements, the provider determines that it supports classifier and flows can be offloaded to the program. The r

[ovs-dev] [RFC PATCH 0/5] XDP offload using flow API provider

This patch adds an XDP-based flow cache using the OVS netdev-offload flow API provider. When a OVS device with XDP offload enabled, packets first are processed in the XDP flow cache (with parse, and table lookup implemented in eBPF) and if hits, the action processing are also done in the context o

[ovs-dev] [RFC PATCH 1/5] netdev-afxdp: Enable loading XDP program.

From: William Tu Now netdev-afxdp always forwards all packets to userspace because it is using libbpf's default XDP program, see 'xsk_load_xdp_prog'. There are some cases when users want to keep packets in kernel instead of sending to userspace, for example, management traffic such as SSH should

Re: [ovs-dev] [PATCH] userspace-tso: Document the minimum kernel version.

On Fri, Mar 06, 2020 at 04:50:38PM +0100, Ilya Maximets wrote: > On 3/2/20 8:51 PM, Flavio Leitner wrote: > > On Mon, Mar 02, 2020 at 01:11:35PM +0100, Ilya Maximets wrote: > >> On 2/28/20 11:58 PM, Flavio Leitner wrote: > >>> The kernel needs to be at least 4.19-rc7 to include the commit > >>> 9d2

[ovs-dev] [PATCH v2] userspace-tso: Document the minimum kernel version.

The kernel needs to be at least 4.19-rc7 to include the commit 9d2f67e43b73 ("net/packet: fix packet drop as of virtio gso") otherwise the TSO packets are dropped when using raw sockets. Fixes: 29cf9c1b3b9c ("userspace: Add TCP Segmentation Offload support") Reported-by: Yi Yang (杨燚)-云服务集团 Signed

[ovs-dev] お支払い方法の情報を更新してください

___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH v2 ovn] logical-fields: fix memory leak caused by initialize ovnfield_by_name twice

On Tue, Mar 10, 2020 at 2:02 PM Numan Siddique wrote: > On Sat, Mar 7, 2020 at 4:42 AM Ben Pfaff wrote: > > > > On Thu, Mar 05, 2020 at 07:21:41AM +0100, Damijan Skvarc wrote: > > > ovnfield_by_name is hash of strings which is used to quickly find > > > field by name. This hash is initialized fr

Re: [ovs-dev] Re： Re: Re: [PATCH v4 0/3] Add support for TSO with DPDK

On Tue, Mar 10, 2020 at 04:08:43PM +0800, txfh2007 wrote: > Hi Flavio and all: > > Is there a way to support software TSO for DPDK tunnel network ? I have > tried userspace TSO function, and running on tunnel network, I have got the > following error: > "Tunneling packets with HW offlo

Re: [ovs-dev] [PATCH v2 ovn] logical-fields: fix memory leak caused by initialize ovnfield_by_name twice

On Sat, Mar 7, 2020 at 4:42 AM Ben Pfaff wrote: > > On Thu, Mar 05, 2020 at 07:21:41AM +0100, Damijan Skvarc wrote: > > ovnfield_by_name is hash of strings which is used to quickly find > > field by name. This hash is initialized from ovn_init_symtab(). In case > > the latter function is called mu

Re: [ovs-dev] L'UNIVERS NOUS A TOUT DONNÉ / THE UNIVERSE HAS GIVEN US EVERYTHING

Bonjour Mme / Mr. Maître absolue vous aide à trouver la solution à Vos problèmes : Amour, chance, travail, santé, commerce, retour de l'être aimé, même dans les cas les plus désespérés, soutien aux entreprises, Désenvoûtement, Amour, argent, travail, talisman, santé, famille, sorcellerie, spiritis

Re: [ovs-dev] [PATCH] travis: Fix using DPDK build from master branch cache.

On Mon, Mar 9, 2020 at 3:40 PM Ilya Maximets wrote: > > If no cache available for current branch, Travis CI uses cache from > the default (master) branch. This causes build failures on older > OVS branches if cache was cleared because DPDK builds from master > branch are not compatible. > > For e

[ovs-dev] Re： Re: Re: [PATCH v4 0/3] Add support for TSO with DPDK

Hi Flavio and all: Is there a way to support software TSO for DPDK tunnel network ? I have tried userspace TSO function, and running on tunnel network, I have got the following error: "Tunneling packets with HW offload flags is not supported: packet dropped" So is there a way to