[ovs-dev] [PATCH 3/6] Make ByteQ safe for simultaneous producer/consumer

From: Anton Ivanov A ByteQ with unlocked head and tail is unsafe for simultaneous consume/produce. If simultaneous use is desired, these either need to be locked or there needs to be a third atomic or lock guarded variable "used". An atomic "used" allows the producer to enqueue safely because i

[ovs-dev] [PATCH 4/6] Fixes for build with extra warnings

From: Anton Ivanov Signed-off-by: Anton Ivanov --- lib/byteq.c | 14 +++--- lib/byteq.h | 12 ++-- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/lib/byteq.c b/lib/byteq.c index da40c2530..8a7b4f1dc 100644 --- a/lib/byteq.c +++ b/lib/byteq.c @@ -38,16 +38,16 @@

[ovs-dev] [PATCH 1/6] Make polling fds persistent

From: Anton Ivanov Saves on: 1. Allocation and disposal of a hash map per iteration in all threads 2. Re-population of the hashmap with all fds per iteration 3. Walking of the hashmap to construct a pollfd array per iteration 4. Allocating/deallocating the pollfd array per iteration 5. Decreases

[ovs-dev] [PATCH 6/6] Disable "merge updates on backlogged connections" test

From: Anton Ivanov The merge on backlogged behavior is predicated on prohibiting processing of incoming transactions while there is an outstanding backlog. This behavior does not make sense if the xmit/recv is async from actual business logic. Signed-off-by: Anton Ivanov --- tests/ovsdb-serve

[ovs-dev] Async IO and other IO improvement patch series

Hi All, These are the IO improvement patch series. Rationale: according to logs and specifically the logging of poll in ovsdb and ovn-northd at high scale the combined IO + processing task will regularly exceed 50% and approach 90% in large scale OVN installs. These patches attempt to decouple I

[ovs-dev] [PATCH 2/6] Enable kernel probes and map stream probes onto them

From: Anton Ivanov 1. Fix probe logic. The stream_or_pstream_needs_probes function returning a mix of integer and boolean. As a result probes were NOT turned off in a number of cases on unix domain sockets and other transports where there should be no probing. It now returns -1 (do not know), 0 (

[ovs-dev] [PATCH 5/6] Introduce async IO in JSONRPC

From: Anton Ivanov 1. Pull out buffering and send/receive ops from json rpc 2. Make the SSL send zero copy (it was creating an ofpbuf out of an existing ofpbuf data without necessity). 3. Add vector IO to stream-fd to make flushing more efficient. Also makes queueing for stream-fd and stream-ss

[ovs-dev] [PATCH 1/2] Add support for parallel processing of hashes

From: Anton Ivanov Adds functionality needed to walk a hash in parallel where thread ID N out of a pool sized M is responcible for processing all elements in buckets N, N+M, N+M*2, etc Signed-off-by: Anton Ivanov --- lib/automake.mk | 2 + lib/fasthmap.c | 367 ++

[ovs-dev] [PATCH 2/2] Run monitor processing in parallel

From: Anton Ivanov Monitor processing performs a full walk of all rows in all tables referenced in a monitor. The rows are internally represented as a hash map. This operation can be run in parallel where thread M out N is walking hash buckets M, N+M, etc. Running inter-thread IPC for only a h

[ovs-dev] Parallel processing of hashmap walks

Hi All, This patchset provides support for parallel processing of some operations on hashes - namely full hash walks. It also enables it in the case where it is applicable and is a known pain point - ovsdb monitors. Parallel walking is enabled only for large hashes. If the size of the hash is les

Re: [ovs-dev] [PATCH v5 0/6] DPCLS Subtable ISA Optimization

> -Original Message- > From: William Tu > Sent: Saturday, July 4, 2020 10:18 PM > To: Van Haaren, Harry > Cc: ovs-dev ; Stokes, Ian ; > Ilya > Maximets ; Federico Iezzi > Subject: Re: [PATCH v5 0/6] DPCLS Subtable ISA Optimization > > On Thu, Jul 2, 2020 at 8:18 AM Van Haaren, Harry >

Re: [ovs-dev] [PATCH 1/6] Make polling fds persistent

Bleep bloop. Greetings Anton Ivanov, 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 is 88 characters long (recommended limit is 79) #124 FILE: lib/poll-loop-unix.c:6

Re: [ovs-dev] [PATCH 2/6] Enable kernel probes and map stream probes onto them

Bleep bloop. Greetings Anton Ivanov, 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 is 102 characters long (recommended limit is 79) #307 FILE: lib/stream-unix.c:65:

Re: [ovs-dev] [PATCH 4/6] Fixes for build with extra warnings

Bleep bloop. Greetings Anton Ivanov, 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. build: /bin/sh ./libtool --tag=CC --mode=compile gcc -std=gnu99 -DHAVE_CONFIG_H -I. -I ./include -I

Re: [ovs-dev] [PATCH 1/2] Add support for parallel processing of hashes

Bleep bloop. Greetings Anton Ivanov, 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: Improper whitespace around control block #443 FILE: lib/fasthmap.h:33: #define HMAP_FOR_

Re: [ovs-dev] [PATCH v2] dpif-netdev-unixctl.man: document bond-show command

On 7/3/20 7:29 PM, Flavio Leitner wrote: > On Fri, Jul 03, 2020 at 06:57:11PM +0200, Adrian Moreno wrote: >> Document recently added ovs-appctl command >> >> Fixes: 9df65060cf4c (userspace: Avoid dp_hash recirculation for balance-tcp >> bond mode.) >> Cc: Vishal Deep Ajmera >> Signed-off-by: Ad

[ovs-dev] [PATCH v3] dpif-netdev-unixctl.man: document bond-show command

Document recently added ovs-appctl command Fixes: ac1d2685ebcd ("dpif-netdev-unixctl.man: document bond-show command") Cc: amore...@redhat.com Signed-off-by: Adrian Moreno --- lib/dpif-netdev-unixctl.man | 9 + 1 file changed, 9 insertions(+) diff --git a/lib/dpif-netdev-unixctl.man b/l

[ovs-dev] [PATCH v4] dpif-netdev-unixctl.man: document bond-show command

Document recently added ovs-appctl command Fixes: 9df65060cf4c ("userspace: Avoid dp_hash recirculation for balance-tcp bond mode.") Cc: vishal.deep.ajm...@ericsson.com Signed-off-by: Adrian Moreno --- lib/dpif-netdev-unixctl.man | 9 + 1 file changed, 9 insertions(+) diff --git a/lib/

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

Hi Shahaji, I have not measured context switch overhead, but I feel it should be acceptable. Because 10Mpps throughput with zero-packet drop(20s) could be achieved in some arm server. Maybe you could make performance profiling on your test bench to find out the root cause of performance degrad

Re: [ovs-dev] [PATCH v3] dpif-netdev-unixctl.man: document bond-show command

Please ignore this patch On 7/6/20 11:25 AM, Adrian Moreno wrote: > Document recently added ovs-appctl command > > Fixes: ac1d2685ebcd ("dpif-netdev-unixctl.man: document bond-show command") > Cc: amore...@redhat.com > Signed-off-by: Adrian Moreno > --- > lib/dpif-netdev-unixctl.man | 9 +++

[ovs-dev] VPNaas support for OVN

Hi everyone, Does OVN support VPNaas? If not, is there any roadmap for it or some WIP? Thanks, Benjamin ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH v1 0/6] Memory access optimization for flow scalability of userspace datapath.

Hi William, Many thanks for your time to test these patches. The number is achieved on Arm server, but x86 has the similar improvement. And CPU cache size will slightly impact the performance data, because the larger cache size, the lower probability of cache refilling/eviction . Best Regards

Re: [ovs-dev] [PATCH v1 0/6] Memory access optimization for flow scalability of userspace datapath.

Hi William, > > On Tue, Jun 2, 2020 at 12:10 AM Yanqin Wei wrote: > > > > OVS userspace datapath is a program with heavy memory access. It needs > > to load/store a large number of memory, including packet header, > > metadata, EMC/SMC/DPCLS tables and so on. It causes a lot of cache > > line mis

Re: [ovs-dev] [PATCH v4 ovn 4/5] ovn-northd: Refactor NAT address parsing.

On Sat, Jul 4, 2020 at 12:05 AM Dumitru Ceara wrote: > Store NAT entries pointers in ovn_datapath and pre-parse the external IP > addresses. This simplifies the code and makes it easier to reuse the parsed > external IP and solicited-node address without reparsing. > > Acked-by: Han Zhou > Signe

Re: [ovs-dev] [PATCH v4 ovn 5/5] ovn-northd: Minimize number of ARP/NS responder flows for DNAT.

On Sat, Jul 4, 2020 at 12:05 AM Dumitru Ceara wrote: > Most ARP/NS responder flows can be configured per datapath instead of per > router port. > > The only exception is with distributed gateway router ports which need > special treatment. This patch changes the ARP/NS responder behavior and > ad

[ovs-dev] [PATCH ovn v5] ovn-northd: Minimize number of ARP/NS responder flows for DNAT.

Most ARP/NS responder flows can be configured per datapath instead of per router port. The only exception is with distributed gateway router ports which need special treatment. This patch changes the ARP/NS responder behavior and adds: - Priority 92 flows to reply to ARP requests on distributed ga

Re: [ovs-dev] [PATCH v4 ovn 4/5] ovn-northd: Refactor NAT address parsing.

On 7/6/20 12:56 PM, Numan Siddique wrote: > > > On Sat, Jul 4, 2020 at 12:05 AM Dumitru Ceara > wrote: > > Store NAT entries pointers in ovn_datapath and pre-parse the external IP > addresses. This simplifies the code and makes it easier to reuse the > pars

Re: [ovs-dev] [PATCH v1 2/6] dpif-netdev: add tunnel_valid flag to skip ip/ipv6 address comparison

Hi Ilya, > > --- > > Hi. > First of all, thanks for working on performance improvements! Thanks, I saw some slides where OVS was used to compare flow scalability with other projects. It inspired me to optimize this code. > > However, this doesn't look as a clean patch. There are some trade-off

Re: [ovs-dev] [PATCH v6 0/6] DPCLS Subtable ISA Optimization

> -Original Message- > From: William Tu > Sent: Sunday, July 5, 2020 3:06 PM > To: Van Haaren, Harry > Cc: ovs-dev ; Stokes, Ian ; > Ilya > Maximets ; Federico Iezzi > Subject: Re: [PATCH v6 0/6] DPCLS Subtable ISA Optimization > > On Thu, Jul 2, 2020 at 10:42 AM Harry van Haaren > wr

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

Hi Yanqin, The drops are random intervals, sometimes I can run for minutes without drops. The case is very borderline with when CPUs are close to 99% and with around 1000 flows. We see the drops once every 10-15 seconds and its random in nature. If I use one ring per core the drops go away, if I en

Re: [ovs-dev] [PATCH v4 3/5] dpif-netdev: Skip encap action during datapath execution

On Sun, Jul 5, 2020 at 7:33 PM Eli Britstein wrote: > > > On 6/29/2020 12:50 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

Re: [ovs-dev] [PATCH] netdev-offload-dpdk: Set transfer attribute to zero for mark/rss offload

A gentle reminder on this patch. Thanks, -Harsha On Mon, Jun 29, 2020 at 11:31 PM Sriharsha Basavapatna wrote: > > The offload layer doesn't initialize the 'transfer' attribute > for mark/rss offload (partial offload). It should be set to 0. > > Fixes: 60e778c7533a ("netdev-offload-dpdk: Framewor

Re: [ovs-dev] [PATCH v4] dpif-netdev-unixctl.man: document bond-show command

On Mon, Jul 06, 2020 at 11:26:55AM +0200, Adrian Moreno wrote: > Document recently added ovs-appctl command > > Fixes: 9df65060cf4c ("userspace: Avoid dp_hash recirculation for balance-tcp > bond mode.") > Cc: vishal.deep.ajm...@ericsson.com > Signed-off-by: Adrian Moreno > --- LGTM Acked-by: F

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

Flavio Leitner writes: > On Wed, Jun 24, 2020 at 09:48:00AM -0400, Aaron Conole wrote: >> Currently, the channel handlers are polled globally. On some >> systems, this causes a thundering herd issue where multiple >> handler threads become active, only to do no work and immediately >> sleep. >>

Re: [ovs-dev] Vhost-user dequeue zero copy removal

On 7/2/2020 12:56 PM, Kevin Traynor wrote: On 02/07/2020 12:18, Stokes, Ian wrote: On 7/1/2020 3:08 PM, Kevin Traynor wrote: On 01/07/2020 13:46, Ilya Maximets wrote: On 7/1/20 1:46 PM, Kevin Traynor wrote: On 01/07/2020 11:28, Stokes, Ian wrote: Hi All, While completing validation wor

Re: [ovs-dev] Vhost-user dequeue zero copy removal

On 06/07/2020 16:30, Stokes, Ian wrote: > > > On 7/2/2020 12:56 PM, Kevin Traynor wrote: >> On 02/07/2020 12:18, Stokes, Ian wrote: >>> >>> >>> On 7/1/2020 3:08 PM, Kevin Traynor wrote: On 01/07/2020 13:46, Ilya Maximets wrote: > On 7/1/20 1:46 PM, Kevin Traynor wrote: >> On 01/07/20

[ovs-dev] [PATCH branch-2.13 v1 1/1] dpdk: Use DPDK 19.11.2 release.

Modify travis linux build script to use DPDK 19.11.2 stable release and update docs to reference 19.11.2 stable release. Signed-off-by: Ian Stokes --- .travis/linux-build.sh | 2 +- Documentation/faq/releases.rst | 2 +- Documentation/intro/install/dpdk.rst | 8 ++

[ovs-dev] [PATCH v1 1/1] dpdk: Use DPDK 19.11.2 release.

Modify travis linux build script to use DPDK 19.11.2 stable release and update docs to reference 19.11.2 stable release. Signed-off-by: Ian Stokes --- .travis/linux-build.sh | 2 +- Documentation/faq/releases.rst | 2 +- Documentation/intro/install/dpdk.rst | 8 ++

Re: [ovs-dev] [PATCHv2] netdev-offload-tc: Add drop action support.

On Sun, Jul 5, 2020 at 9:49 PM Tonghao Zhang wrote: > > On Sun, Jul 5, 2020 at 5:34 AM William Tu wrote: > > > > Currently drop action is not offloaded when using userspace datapath > > with tc offload. The patch programs tc gact (generic action) chain > > ID 0 to drop the packet by setting it t

[ovs-dev] お支払い方法の情報を更新

お支払い方法の情報を更新してください。Update default card for your membership. マイストア? タイムセール? ギフト券 Amazonプライムをご利用頂きありがとうございます。お客様のAmazonプライム会員資格は、2020/07/09に更新を迎えます。お調べしたところ、会費のお支払いに使用できる有効なクレジットカードがアカウントに登録されていません。クレジットカード情報の更新、新しいクレジットカードの追加については以下の手順をご確認ください。 1. アカウントサービスからAmazonプライム会員情報を管理するにアクセスします。

Re: [ovs-dev] [ovs-discuss] OVS 2.12/2.13 compilation on Ubuntu Bionic

On 6/29/20 8:45 PM, Gregory Rose wrote: > > > On 6/26/2020 4:57 AM, Maciej Jozefczyk wrote: >> Hello! >> >> I would like to kindly ask You if there is a possibility to cherry-pick >> patch [1] to stable branches OVS 2.12, OVS 2.13 and release new tags for it? >> >> Without this patch we're now un

Re: [ovs-dev] [PATCH v6 0/6] DPCLS Subtable ISA Optimization

On 7/5/2020 3:06 PM, William Tu wrote: On Thu, Jul 2, 2020 at 10:42 AM Harry van Haaren wrote: v6 work done: - Fix as --64 unrecognized option - Fix build issues with avx512 library changes - Fix files left in build dir after distclean - Fix CPU arch dependant RTE_CPUFLAG_ usage Thanks Wil

Re: [ovs-dev] [PATCH] ovsdb: Remove duplicated include.

Hi wangyunjian. I'm probably not the right person to address this to; I no longer consider myself a general reviewer for every patch. On Wed, Jul 01, 2020 at 10:36:07AM +, wangyunjian wrote: > Friendly ping. > > > -Original Message- > > From: wangyunjian > > Sent: Friday, May 15, 202

Re: [ovs-dev] [PATCH ovn] ovn-detrace: Fix typo in manpage.

On Thu, Jun 18, 2020 at 07:09:11PM +0200, Dumitru Ceara wrote: > On 6/18/20 1:07 AM, Ben Pfaff wrote: > > Signed-off-by: Ben Pfaff > > --- > > utilities/ovn-detrace.1.in | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff --git a/utilities/ovn-detrace.1.in b/utilities/ovn-detr

[ovs-dev] [PATCH v2 3/5] conntrack: Rename "master" connection to "primary" connection.

Signed-off-by: Ben Pfaff --- include/openvswitch/meta-flow.h | 14 +++ lib/conntrack-private.h | 10 ++--- lib/conntrack.c | 74 - lib/ct-dpif.c | 6 +-- lib/ct-dpif.h | 2 +- lib/meta-flow.xml

[ovs-dev] [PATCH v2 5/5] checkpatch: Add argument to skip gerrit change id check

From: Roi Dayan This arg can be used internally by groups using gerrit for code reviews. Signed-off-by: Roi Dayan Signed-off-by: Ben Pfaff --- utilities/checkpatch.py | 9 +++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/utilities/checkpatch.py b/utilities/checkpatch.py

[ovs-dev] [PATCH v2 4/5] Eliminate "whitelist" and "blacklist" terms.

There is one remaining use under datapath. That change should happen upstream in Linux first according to our usual policy. Signed-off-by: Ben Pfaff --- Documentation/howto/ipsec.rst | 2 +- Documentation/howto/selinux.rst | 8 +-- Documentation/topics/datapath.r

[ovs-dev] [PATCH v2 0/5] Use more sensitive terminology.

There's no value in risking turning people away from OVS due to insensitive terminology choices. We can do better. v1->v2: Rebase. Ben Pfaff (4): Eliminate use of term "slave" in bond, LACP, and bundle contexts. Use primary/secondary, not master/slave, as names for OpenFlow roles. conntrac

[ovs-dev] [PATCH v2 2/5] Use primary/secondary, not master/slave, as names for OpenFlow roles.

Signed-off-by: Ben Pfaff --- Documentation/topics/design.rst | 110 +++--- NEWS | 2 + include/openflow/nicira-ext.h| 22 ++--- include/openflow/openflow-1.2.h | 6 +- include/openflow/openflow-1.4.h | 8 +- include/ope

Re: [ovs-dev] [PATCH v2] ofproto-dpif-trace: Improve NAT tracing.

On Wed, Jun 17, 2020 at 09:21:57AM +0200, Dumitru Ceara wrote: > On 6/17/20 12:07 AM, Ben Pfaff wrote: > > On Fri, Jan 10, 2020 at 10:34:43AM +0100, Dumitru Ceara wrote: > >> When ofproto/trace detects a recirc action it resumes execution at the > >> specified next table. However, if the ct action

Re: [ovs-dev] [PATCH] odp-util.c: Fix dp_hash execution with slowpath actions.

On Tue, Jun 16, 2020 at 03:51:06PM -0700, Han Zhou wrote: > Thanks Ben. I think it is better to be backported to at least 2.12, 2.11. I > am not sure about older branches. I guess 2.13, then, as well. Would you mind posting backport patches? I see that there are patch rejects, although they are

Re: [ovs-dev] [PATCH] meta-flow: Document that constituents of conjunctive flows may overlap.

On Thu, May 28, 2020 at 05:11:53PM -0700, William Tu wrote: > On Wed, May 27, 2020 at 12:24:31PM -0700, Ben Pfaff wrote: > > Suggested-by: Antonin Bas > > Signed-off-by: Ben Pfaff > > --- > > lib/meta-flow.xml | 2 ++ > > manpages.mk | 3 --- > > 2 files changed, 2 insertions(+), 3 deletio

Re: [ovs-dev] [PATCH v2 1/5] Eliminate use of term "slave" in bond, LACP, and bundle contexts.

Bleep bloop. Greetings Ben Pfaff, 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 is 91 characters long (recommended limit is 79) #1701 FILE: lib/lacp.c:1160: lacp_get

Re: [ovs-dev] [PATCH v2 2/5] Use primary/secondary, not master/slave, as names for OpenFlow roles.

Bleep bloop. Greetings Ben Pfaff, 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: .git/rebase-apply/patch:42: trailing whitespace. primary/

Re: [ovs-dev] [PATCH ovn] Correctly document maximum tunnel key for port bindings.

On Thu, Apr 09, 2020 at 11:36:22PM +0200, Dumitru Ceara wrote: > On 4/9/20 9:10 PM, Ben Pfaff wrote: > > Only the lower half of the 16-bit range is available for individual > > port bindings. The upper half of the range is reserved for multicast > > groups. > > > > Signed-off-by: Ben Pfaff > >

Re: [ovs-dev] [PATCH] python: Fix plural forms of OVSDB types.

This still needs a review. On Sat, Mar 21, 2020 at 03:17:27PM -0700, Ben Pfaff wrote: > Fixes two problems. First, the plural of chassis is also chassis. > Second, for linguistic analysis we need to consider plain words, not > words that have (e.g.) \fB and \fR pasted into them for nroff output.

Re: [ovs-dev] Running wireguard tunnel in Open vSwitch

On 03/07/2020 09:20, Pratik Panjwani wrote: > Hi All, > > I am trying to extend my L2 network across sites using wireguard as my VPN. > The networking internally across VMs in a site is managed using > openvswitch. I have established the connectivity between the WG Client and > WG server(tunnel end

[ovs-dev] お支払い方法の情報を更新

お支払い方法の情報を更新してください。Update default card for your membership. マイストア? タイムセール? ギフト券 Amazonプライムをご利用頂きありがとうございます。お客様のAmazonプライム会員資格は、2020/07/09に更新を迎えます。お調べしたところ、会費のお支払いに使用できる有効なクレジットカードがアカウントに登録されていません。クレジットカード情報の更新、新しいクレジットカードの追加については以下の手順をご確認ください。 1. アカウントサービスからAmazonプライム会員情報を管理するにアクセスします。

[ovs-dev] お支払い方法の情報を更新

お支払い方法の情報を更新してください。Update default card for your membership. マイストア? タイムセール? ギフト券 Amazonプライムをご利用頂きありがとうございます。お客様のAmazonプライム会員資格は、2020/07/09に更新を迎えます。お調べしたところ、会費のお支払いに使用できる有効なクレジットカードがアカウントに登録されていません。クレジットカード情報の更新、新しいクレジットカードの追加については以下の手順をご確認ください。 1. アカウントサービスからAmazonプライム会員情報を管理するにアクセスします。

Re: [ovs-dev] [PATCH ovn v5] ovn-northd: Minimize number of ARP/NS responder flows for DNAT.

On Mon, Jul 6, 2020 at 4:33 AM Dumitru Ceara wrote: > > Most ARP/NS responder flows can be configured per datapath instead of per > router port. > > The only exception is with distributed gateway router ports which need > special treatment. This patch changes the ARP/NS responder behavior and adds

Re: [ovs-dev] [PATCH] odp-util.c: Fix dp_hash execution with slowpath actions.

On Mon, Jul 6, 2020 at 1:42 PM Ben Pfaff wrote: > > On Tue, Jun 16, 2020 at 03:51:06PM -0700, Han Zhou wrote: > > Thanks Ben. I think it is better to be backported to at least 2.12, 2.11. I > > am not sure about older branches. > > I guess 2.13, then, as well. Yes, sorry I forgot to mention 2.13.

Re: [ovs-dev] [PATCH] odp-util.c: Fix dp_hash execution with slowpath actions.

On Mon, Jul 06, 2020 at 04:06:48PM -0700, Han Zhou wrote: > On Mon, Jul 6, 2020 at 1:42 PM Ben Pfaff wrote: > > > > On Tue, Jun 16, 2020 at 03:51:06PM -0700, Han Zhou wrote: > > > Thanks Ben. I think it is better to be backported to at least 2.12, > 2.11. I > > > am not sure about older branches.

Re: [ovs-dev] [PATCH v2 1/5] Eliminate use of term "slave" in bond, LACP, and bundle contexts.

On 7/6/20 10:35 PM, Ben Pfaff wrote: > Most of these changes should not change user-visible behavior. One > place where they do is in "ovs-ofctl dump-flows", which will now output > "subs:..." inside "bundle" actions instead of "slaves:...". I don't > expect this to cause real problems in most sy

Re: [ovs-dev] [PATCH v4] dpif-netdev-unixctl.man: document bond-show command

On 7/6/20 4:34 PM, Flavio Leitner wrote: > On Mon, Jul 06, 2020 at 11:26:55AM +0200, Adrian Moreno wrote: >> Document recently added ovs-appctl command >> >> Fixes: 9df65060cf4c ("userspace: Avoid dp_hash recirculation for balance-tcp >> bond mode.") >> Cc: vishal.deep.ajm...@ericsson.com >> Signe

Re: [ovs-dev] [PATCH v2] odp-execute: Fix length checking while executing check_pkt_len action.

On 6/26/20 12:51 PM, Ilya Maximets wrote: > If dp-packet contains l2 padding or cutlen was applied to it, size will > be larger than the actual size of a payload and action will work > incorrectly. > > Ex. Padding could be added during miniflow_extract() if detected. > > CC: Numan Siddique > Fix

Re: [ovs-dev] [PATCH] ofproto: delete buckets when lb_output is false

On 6/26/20 1:51 PM, Adrian Moreno wrote: > When lb-output-action is toggled back to "false" buckets are not being > deleted. Delete them as they will no longer be used. > > Add unit test to verify buckets are correctly deleted. Thanks! Applied. Best regards, Ilya Maximets. __

Re: [ovs-dev] [PATCH ovs] dpif-netdev: Delete the flow limit in dpif-netdev

On 6/16/20 2:15 PM, Tonghao Zhang wrote: > On Tue, Jun 16, 2020 at 8:12 PM Tonghao Zhang > wrote: >> >> On Mon, Mar 16, 2020 at 7:17 PM wrote: >>> >>> From: Tonghao Zhang >>> >>> The max number of flow in dpif-netdev is MAX_FLOWS, >>> the previous patch[1] try to install more flows, >>> and int

Re: [ovs-dev] [PATCH] ovsdb: Remove duplicated include.

On 5/15/20 1:21 PM, wangyunjian wrote: > From: Yunjian Wang > > Signed-off-by: Yunjian Wang > --- > ovsdb/monitor.c | 1 - > ovsdb/rbac.c| 1 - > 2 files changed, 2 deletions(-) > > diff --git a/ovsdb/monitor.c b/ovsdb/monitor.c > index 1c66b42..532dedc 100644 > --- a/ovsdb/monitor.c > +++

Re: [ovs-dev] [PATCH] python: Fix plural forms of OVSDB types.

On Tue, Jul 7, 2020, 2:38 AM Ben Pfaff wrote: > This still needs a review. > Oops. Sorry about that. Acked-by: Numan Siddique > On Sat, Mar 21, 2020 at 03:17:27PM -0700, Ben Pfaff wrote: > > Fixes two problems. First, the plural of chassis is also chassis. > > Second, for linguistic analysi

Re: [ovs-dev] [PATCHv2] netdev-offload-tc: Add drop action support.

On Tue, Jul 7, 2020 at 12:14 AM William Tu wrote: > > On Sun, Jul 5, 2020 at 9:49 PM Tonghao Zhang wrote: > > > > On Sun, Jul 5, 2020 at 5:34 AM William Tu wrote: > > > > > > Currently drop action is not offloaded when using userspace datapath > > > with tc offload. The patch programs tc gact (

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

Hi Shahaji, It seems to be caused by some periodic task. In the pmd thread, pmd auto load balance would be done periodically. /* Time in microseconds of the interval in which rxq processing cycles used * in rxq to pmd assignments is measured and stored. */ #define PMD_RXQ_INTERVAL_LEN 1000LL

[ovs-dev] [PATCHv3] netdev-offload-tc: Add drop action support.

Currently drop action is not offloaded when using userspace datapath with tc offload. The patch programs tc gact (generic action) chain ID 0 to drop the packet by setting it to TC_ACT_SHOT. Example: $ ovs-appctl dpctl/add-flow netdev@ovs-netdev \ 'recirc_id(0),in_port(2),eth(),eth_type(0x0806),

[ovs-dev] お支払い方法の情報を更新

お支払い方法の情報を更新してください。Update default card for your membership. マイストア? タイムセール? ギフト券 Amazonプライムをご利用頂きありがとうございます。お客様のAmazonプライム会員資格は、2020/06/09に更新を迎えます。お調べしたところ、会費のお支払いに使用できる有効なクレジットカードがアカウントに登録されていません。クレジットカード情報の更新、新しいクレジットカードの追加については以下の手順をご確認ください。 1. アカウントサービスからAmazonプライム会員情報を管理するにアクセスします。

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

Thanks Yangin, What does this define mean? Every 10 second some kind of book keeping of the packet processing cycles ? Are you saying to make this even bigger in time. 1000 seconds or something? If I want to disable what do I do? Thanks, Shahaji On Mon, Jul 6, 2020 at 10:30 PM Yanqin Wei wrote:

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

Hi Shahaji, Yes, update some counter each 10 second for pmd balance and pmd info collection. I have no idea of how to disable them from outside. You could try to modify the following number and observe packet loss. /* Time in microseconds of the interval in which rxq processing cycles used * in

Re: [ovs-dev] [PATCHv3] netdev-offload-tc: Add drop action support.

On Tue, Jul 7, 2020 at 11:11 AM William Tu wrote: > > Currently drop action is not offloaded when using userspace datapath > with tc offload. The patch programs tc gact (generic action) chain > ID 0 to drop the packet by setting it to TC_ACT_SHOT. > > Example: > $ ovs-appctl dpctl/add-flow netdev

Re: [ovs-dev] 10-25 packet drops every few (10-50) seconds TCP (iperf3)

The 2nd one is another periodic task for dpcls ranking. From: Yanqin Wei Sent: Tuesday, July 7, 2020 1:19 PM To: Shahaji Bhosle Cc: Flavio Leitner ; ovs-dev@openvswitch.org; nd ; Ilya Maximets ; Lee Reed ; Vinay Gupta ; Alex Barba Subject: RE: [ovs-dev] 10-25 packet drops every few (10-50) se

Re: [ovs-dev] FWD: Re: DETAILS - APPLY : Available

BUSINESS / PERSONAL LOAN OFFER APR 2.5% - 30 YEARS REPAYMENT NO UPFRONT COST CONFIDENTIAL APPLICATION GRACE PERIOD : YES FINANCE COMPANY: DIRECT FUNDING AUSTRALIA Dear Candidate, Our commercial loan application is available. Contact us / details below and we will get back to you w

[ovs-dev] [PATCH v2] ofproto: delete buckets when lb_output is false

When lb-output-action is toggled back to "false" buckets are not being deleted. Delete them as they will no longer be used. Add unit test to verify buckets are correctly deleted. Fixes: 9df65060cf4c ("userspace: Avoid dp_hash recirculation for balance-tcp bond mode.") Cc: vishal.deep.ajm...@eric