Re: [ovs-dev] [PATCH v2 2/2] ovs-ofctl: Add "compose-packet" command for testing flow_compose().

Thanks for the patch. Tested and looks good to me. I feel it may be a little better if the comment is changed like below: - * can do something like "ovs-ofctl compose-packet udp | tcpdump - -r-" to + * can do something like "ovs-ofctl compose-packet udp --pcap | tcpdump - -r-" to Tested

Re: [ovs-dev] [PATCH v2 1/2] flow: Add some L7 payload data to most L4 protocols that accept it.

Thanks for the patch. Tested and looks good to me. Tested-by: Yifeng Sun Reviewed-by: Yifeng Sun On Fri, Jan 26, 2018 at 3:03 PM, Ben Pfaff wrote: > This makes traffic generated by flow_compose() look slightly more > realistic. It requires lots of updates to tests, but at least the tests >

[ovs-dev] Cómo ser feliz en mi trabajo

Cómo ser feliz en mi trabajo Febrero 21 - webinar Interactivo Introducción: Arturo Villegas es Conferencista Internacional, habiendo impartido más de 600 conferencias en más de 10 años de trayectoria profesional. Es pionero y experto en el tema de la felicidad laboral aplicada a la productivi

Re: [ovs-dev] [PATCH 3/4] flow: Add some L7 payload data to most L4 protocols that accept it.

On Fri, Jan 26, 2018 at 01:52:09PM -0800, Yifeng Sun wrote: > Hi Ben, > > I found an issue in the lines below. It looks like that the 'else if' part > is redundant. > > +if (dp_packet_size(packet) < packet_size) { > +packet_expand(packet, &flow, packet_size); > +} else

[ovs-dev] [PATCH v2 1/2] flow: Add some L7 payload data to most L4 protocols that accept it.

This makes traffic generated by flow_compose() look slightly more realistic. It requires lots of updates to tests, but at least the tests themselves should be slightly more realistic too. At the same time, add --l7 and --l7-len options to ofproto/trace to allow users to specify the amount or cont

[ovs-dev] [PATCH v2 2/2] ovs-ofctl: Add "compose-packet" command for testing flow_compose().

I don't feel obligated to add a bunch of automatic tests for flow_compose(), but this is handy for manual testing or for simple packet generation. Signed-off-by: Ben Pfaff --- utilities/ovs-ofctl.c | 72 +++ 1 file changed, 72 insertions(+) diff -

[ovs-dev] [PATCH v2 0/2] make composed packets more realistic

v1->v2: - Applied and dropped patches 1 and 2. - Fixed bug in patch 3 (thanks Yifeng!). Ben Pfaff (2): flow: Add some L7 payload data to most L4 protocols that accept it. ovs-ofctl: Add "compose-packet" command for testing flow_compose(). NEWS | 2 + lib/flow.c

Re: [ovs-dev] [PATCH 3/5] ovs-vsctl, vtep-ctl: Free 'args' string on exit.

On Fri, Jan 26, 2018 at 07:45:26AM -0800, William Tu wrote: > On Thu, Jan 25, 2018 at 3:39 PM, Ben Pfaff wrote: > > This avoids a memory leak warning from valgrind. > > > > ovn-sbctl and ovn-nbctl already followed this pattern. > > > > Signed-off-by: Ben Pfaff > > --- > > Looks good to me. > >

Re: [ovs-dev] [PATCH 3/4] flow: Add some L7 payload data to most L4 protocols that accept it.

Hi Ben, I found an issue in the lines below. It looks like that the 'else if' part is redundant. +if (dp_packet_size(packet) < packet_size) { +packet_expand(packet, &flow, packet_size); +} else if (dp_packet_size(packet) < packet_size){ +dp_packet_delete(pa

Re: [ovs-dev] [PATCH] rhel: Change depmod configuration

On 1/26/2018 10:41 AM, Flavio Leitner wrote: On Fri, Jan 26, 2018 at 10:03:53AM -0800, Gregory Rose wrote: On 1/26/2018 5:30 AM, Flavio Leitner wrote: Regarding to change --add-modules to --add-kernel, well, I don't see how that is helping. Maybe I am missing something, but every time a kernel

[ovs-dev] OVS DPDK: dpdk_merge pull request for branch-2.7

Hi Ben, The following changes since commit 8add6d8c14597c07a28fda92aeaf9a89ce9baac2: ofproto: Fix double-unref of temporary rule when learning. (2018-01-26 12:30:56 -0800) are available in the git repository at: https://github.com/istokes/ovs dpdk_merge_2_7 for you to fetch changes up to

[ovs-dev] OVS DPDK: dpdk_merge pull request for branch-2.9

Hi Ben, The following changes since commit a8b629f86dacc66ea3b1c37dd1eb539128bcc40c: ofproto: Fix double-unref of temporary rule when learning. (2018-01-26 12:30:47 -0800) are available in the git repository at: https://github.com/istokes/ovs dpdk_merge_2_9 for you to fetch changes up to

[ovs-dev] OVS DPDK: dpdk_merge pull request for branch-2.8

Hi Ben, The following changes since commit dff4aa1bc16ee5173b6af7bb2c0472d7c1c63939: ofproto: Fix double-unref of temporary rule when learning. (2018-01-26 12:30:52 -0800) are available in the git repository at: https://github.com/istokes/ovs dpdk_merge_2_8 for you to fetch changes up to

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

Hi Ben, The following changes since commit 8df9a0c4108be3b1729fd72707d062008d74ef2e: checkpatch.py: Fix Python style. (2018-01-26 12:51:18 -0800) are available in the git repository at: https://github.com/istokes/ovs dpdk_merge for you to fetch changes up to ac1a9bb93fb1d2d60bae64aa7778a4c

Re: [ovs-dev] [PATCH] checkpatch.py: Fix Python style.

Thanks, applied to master. On Fri, Jan 26, 2018 at 12:36:37PM -0800, Justin Pettit wrote: > D’oh. > > Acked-by: Justin Pettit > > --Justin > > > > On Jan 26, 2018, at 11:46 AM, Ben Pfaff wrote: > > > > Fixes the following warnings: > > > > ../utilities/checkpatch.py:219:1: E302 expected 2

Re: [ovs-dev] [PATCH] checkpatch.py: Fix Python style.

D’oh. Acked-by: Justin Pettit --Justin > On Jan 26, 2018, at 11:46 AM, Ben Pfaff wrote: > > Fixes the following warnings: > > ../utilities/checkpatch.py:219:1: E302 expected 2 blank lines, found 1 > ../utilities/checkpatch.py:224:1: E302 expected 2 blank lines, found 1 > ../utilities/checkp

Re: [ovs-dev] [PATCH 1/5] ofproto: Fix double-unref of temporary rule when learning.

On Fri, Jan 26, 2018 at 07:40:37AM -0800, William Tu wrote: > On Thu, Jan 25, 2018 at 3:39 PM, Ben Pfaff wrote: > > When ofproto_flow_mod_init() accepts a rule, it takes ownership of it and > > either unrefs it on error or transfers ownership to the struct it > > initializes on success, but ofprot

[ovs-dev] [PATCH] checkpatch.py: Fix Python style.

Fixes the following warnings: ../utilities/checkpatch.py:219:1: E302 expected 2 blank lines, found 1 ../utilities/checkpatch.py:224:1: E302 expected 2 blank lines, found 1 ../utilities/checkpatch.py:228:1: E302 expected 2 blank lines, found 1 CC: Justin Pettit Fixes: 4e99b70dfae0 ("checkpatch.py

Re: [ovs-dev] [PATCH] ovs-atomic: Fix typo in comment.

On Thu, Jan 25, 2018 at 04:41:02PM -0800, Justin Pettit wrote: > > > On Jan 25, 2018, at 11:51 AM, Ben Pfaff wrote: > > > > Signed-off-by: Ben Pfaff > > --- > > lib/ovs-atomic.h | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff --git a/lib/ovs-atomic.h b/lib/ovs-atomic.h >

[ovs-dev] Dirija sus finanzas de su empresa con éxito

Conozca y dirija sus finanzas de su empresa con éxito Finanzas prácticas para no financieros 14 de Febrero- CP. Hugo Coca Chávez - 9am- 8pm Fundamentar la toma de decisiones financieras a través del conocimiento de distintas herramientas que permiten resolver problemas personales y empresarial

Re: [ovs-dev] [PATCH] rhel: Change depmod configuration

On Fri, Jan 26, 2018 at 10:03:53AM -0800, Gregory Rose wrote: > On 1/26/2018 5:30 AM, Flavio Leitner wrote: > > Regarding to change --add-modules to --add-kernel, well, I don't see > > how that is helping. Maybe I am missing something, but every time a > > kernel is installed, it will run weak-modu

Re: [ovs-dev] [PATCH v3 0/6] Add minimum network namespace support.

Hi Ben, On Wed, Jan 10, 2018 at 04:07:38PM -0800, Ben Pfaff wrote: > Thanks for the series. I actually think that it's pretty close. For > me, this series falls into the category of "obviously the right > direction but impossible to fully validate before applying it". It > builds fine and I wa

Re: [ovs-dev] [PATCH] rhel: Change depmod configuration

On 1/26/2018 5:30 AM, Flavio Leitner wrote: On Wed, Jan 24, 2018 at 07:23:06PM -0800, Greg Rose wrote: A previous patch added post install and post uninstall scripts which use the weak-modules utility to make sure that openvswitch kernel modules are copied to the correct kernel directory. While

Re: [ovs-dev] [PATCH] gre: strip gre-tso offload flags

Thanks wenxu and Greg. I backported as far as branch-2.6. On Fri, Jan 26, 2018 at 05:20:14PM +0800, wenxu wrote: > > > I also it should backport to branch-2.6~2.8 > > > > > > > At 2018-01-26 08:16:54, "Gregory Rose" wrote: > >On 1/25/2018 10:22 AM, Ben Pfaff wrote: > >> On Thu, Jan 25, 2

Re: [ovs-dev] [PATCH] poc: Introduce Proof of Concepts (Package building)

On 1/19/2018 7:55 PM, Ansis Atteka wrote: From: Ansis Atteka This patch sets up foundations for Proof of Concepts that simply materialize documentation into Ansible instructions executed in virtualized Vagrant environment. This Proof of Concept allows to easily build: 1. *.deb packages on Ubun

[ovs-dev] MICROSOFT WARNING NOTIFICATION

MICROSOFT WARNING NOTIFICATION Your E-mail box account will be suspended if not verify due to irregularities in your E-mail box account. Do verify as soon as possible Microsoft Verify Team Microsoft Outlook Copyright © 2018.

[ovs-dev] Expecting you Respond

Dear Sir Madam I am *James f Entwistle* I have a deposit valued at $6.5 million which Recently, I decided to donate this fund to either an organization or devoted individual that will utilize this money the way I will instruct herein. As soon as I receive your reply on Email: *jamesfentwistl.

Re: [ovs-dev] [PATCH v8 1/3] netdev: Add optional qfill output parameter to rxq_recv()

> > @@ -1795,11 +1795,24 @@ netdev_dpdk_vhost_rxq_recv(struct > > netdev_rxq *rxq, > > batch->count = nb_rx; > > dp_packet_batch_init_packet_fields(batch); > > > > +if (qfill) { > > +if (nb_rx == NETDEV_MAX_BURST) { > > +/* The DPDK API returns a uint32_t which oft

Re: [ovs-dev] [PATCH v8 1/3] netdev: Add optional qfill output parameter to rxq_recv()

LGTM but one thing I don't understand down below... > -Original Message- > From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] > Sent: Friday, January 26, 2018 12:20 PM > To: d...@openvswitch.org > Cc: ktray...@redhat.com; Stokes, Ian ; > i.maxim...@samsung.com; O Mahony, Billy ; > Jan

Re: [ovs-dev] [PATCH 3/5] ovs-vsctl, vtep-ctl: Free 'args' string on exit.

On Thu, Jan 25, 2018 at 3:39 PM, Ben Pfaff wrote: > This avoids a memory leak warning from valgrind. > > ovn-sbctl and ovn-nbctl already followed this pattern. > > Signed-off-by: Ben Pfaff > --- Looks good to me. Acked-by: William Tu > utilities/ovs-vsctl.c | 12 > vtep/vtep-ctl

Re: [ovs-dev] [PATCH 2/5] ofproto: Avoid use-after-free on error path in ofproto_flow_mod_learn().

On Thu, Jan 25, 2018 at 3:39 PM, Ben Pfaff wrote: > In the case where the learned flow limit has been reached (below_limit == > false), ofproto_flow_mod_uninit() would unref ofm->temp_rule (which is > also in the 'rule' local variable) before dereferencing rule->flow_cookie > for the log message.

Re: [ovs-dev] [PATCH 1/5] ofproto: Fix double-unref of temporary rule when learning.

On Thu, Jan 25, 2018 at 3:39 PM, Ben Pfaff wrote: > When ofproto_flow_mod_init() accepts a rule, it takes ownership of it and > either unrefs it on error or transfers ownership to the struct it > initializes on success, but ofproto_flow_mod_init_for_learn() was unref-ing > it a second time if it r

Re: [ovs-dev] [PATCH] rhel: Change depmod configuration

On Wed, Jan 24, 2018 at 07:23:06PM -0800, Greg Rose wrote: > A previous patch added post install and post uninstall scripts which > use the weak-modules utility to make sure that openvswitch kernel > modules are copied to the correct kernel directory. While this > patch did fix some issues there a

Re: [ovs-dev] [PATCH v3 3/3] xlate: call tnl_neigh_snoop() from terminate_native_tunnel()

Hi, I've been investigating the failing unit test. I can confirm, it does fail with my series on master. However, when I created the series and sent it to the mailing list it did not. I've rebased my series to this commit before I sent it to the mailing list. commit f59cb331c481d08f9a851c07cf3

Re: [ovs-dev] [PATCH v6 0/6] OVS-DPDK flow offload with rte_flow

> -Original Message- > From: Yuanhan Liu [mailto:y...@fridaylinux.org] > Sent: Friday, January 26, 2018 12:48 PM > To: d...@openvswitch.org > Cc: Stokes, Ian ; Yuanhan Liu > Subject: [PATCH v6 0/6] OVS-DPDK flow offload with rte_flow > > Hi, > > Here is a joint work from Mellanox and Nap

[ovs-dev] [PATCH v6 6/6] Documentation: document ovs-dpdk flow offload

And mark it as experimental. Signed-off-by: Yuanhan Liu --- Documentation/howto/dpdk.rst | 17 + NEWS | 1 + 2 files changed, 18 insertions(+) diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst index 40f9d96..047525c 100644 --- a/Do

[ovs-dev] [PATCH v6 5/6] dpif-netdev: do hw flow offload in a thread

Currently, the major trigger for hw flow offload is at upcall handling, which is actually in the datapath. Moreover, the hw offload installation and modification is not that lightweight. Meaning, if there are so many flows being added or modified frequently, it could stall the datapath, which could

[ovs-dev] [PATCH v6 4/6] netdev-dpdk: add debug for rte flow patterns

For debug purpose. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen v5: - turned log to DBG level --- lib/netdev-dpdk.c | 177 ++ 1 file changed, 177 insertions(+) diff --git a/lib/netdev-dpdk

[ovs-dev] [PATCH v6 3/6] netdev-dpdk: implement flow offload with rte flow

From: Finn Christensen The basic yet the major part of this patch is to translate the "match" to rte flow patterns. And then, we create a rte flow with MARK + RSS actions. Afterwards, all packets match the flow will have the mark id in the mbuf. The reason RSS is needed is, for most NICs, a MARK

[ovs-dev] [PATCH v6 1/6] dpif-netdev: associate flow with a mark id

Most modern NICs have the ability to bind a flow with a mark, so that every packet matches such flow will have that mark present in its descriptor. The basic idea of doing that is, when we receives packets later, we could directly get the flow from the mark. That could avoid some very costly CPU o

[ovs-dev] [PATCH v6 2/6] dpif-netdev: retrieve flow directly from the flow mark

So that we could skip some very costly CPU operations, including but not limiting to miniflow_extract, emc lookup, dpcls lookup, etc. Thus, performance could be greatly improved. A PHY-PHY forwarding with 1000 mega flows (udp,tp_src=1000-1999) and 1 million streams (tp_src=1000-1999, tp_dst=2000-2

[ovs-dev] [PATCH v6 0/6] OVS-DPDK flow offload with rte_flow

Hi, Here is a joint work from Mellanox and Napatech, to enable the flow hw offload with the DPDK generic flow interface (rte_flow). The basic idea is to associate the flow with a mark id (a unit32_t number). Later, we then get the flow directly from the mark id, which could bypass some heavy CPU

[ovs-dev] [PATCH v8 3/3] dpif-netdev: Detection and logging of suspicious PMD iterations

This patch enhances dpif-netdev-perf to detect iterations with suspicious statistics according to the following criteria: - iteration lasts longer than US_THR microseconds (default 250). This can be used to capture events where a PMD is blocked or interrupted for such a period of time that the

[ovs-dev] [PATCH v8 2/3] dpif-netdev: Detailed performance stats for PMDs

This patch instruments the dpif-netdev datapath to record detailed statistics of what is happening in every iteration of a PMD thread. The collection of detailed statistics can be controlled by a new Open_vSwitch configuration parameter "other_config:pmd-perf-metrics". By default it is disabled. T

[ovs-dev] [PATCH v8 1/3] netdev: Add optional qfill output parameter to rxq_recv()

If the caller provides a non-NULL qfill pointer and the netdev implemementation supports reading the rx queue fill level, the rxq_recv() function returns the remaining number of packets in the rx queue after reception of the packet burst to the caller. If the implementation does not support this, i

[ovs-dev] [PATCH v8 0/3] dpif-netdev: Detailed PMD performance metrics and supervision

The run-time performance of PMDs is often difficult to understand and trouble-shoot. The existing PMD statistics counters only provide a coarse grained average picture. At packet rates of several Mpps sporadic drops of packet bursts happen at sub-millisecond time scales and are impossible to capt

Re: [ovs-dev] [PATCH v7 3/3] dpif-netdev: Detection and logging of suspicious PMD iterations

Thanks for the review. Issues will be addressed in v8. Please find answers below. /Jan > -Original Message- > From: O Mahony, Billy [mailto:billy.o.mah...@intel.com] > Sent: Friday, 19 January, 2018 18:11 > To: Jan Scheurich ; d...@openvswitch.org > Cc: ktray...@redhat.com; Stokes, Ian ;

Re: [ovs-dev] [PATCH v7 3/3] dpif-netdev: Detection and logging of suspicious PMD iterations

Thanks for the review. Issues addressed in v8. /Jan > -Original Message- > From: O Mahony, Billy [mailto:billy.o.mah...@intel.com] > Sent: Friday, 19 January, 2018 12:07 > To: Jan Scheurich ; d...@openvswitch.org > Cc: ktray...@redhat.com; Stokes, Ian ; > i.maxim...@samsung.com > Subject:

Re: [ovs-dev] [PATCH v7 2/3] dpif-netdev: Detailed performance stats for PMDs

Thanks for the review. Find my answers below. /Jan > -Original Message- > From: O Mahony, Billy [mailto:billy.o.mah...@intel.com] > Sent: Friday, 19 January, 2018 12:31 > To: Jan Scheurich ; d...@openvswitch.org > Cc: ktray...@redhat.com; Stokes, Ian ; > i.maxim...@samsung.com > Subject:

Re: [ovs-dev] [PATCH v5 1/5] dpif-netdev: associate flow with a mark id

On Fri, Jan 26, 2018 at 10:49:46AM +, Stokes, Ian wrote: > > > > +static int > > > > +mark_to_flow_disassociate(struct dp_netdev_pmd_thread *pmd, > > > > + struct dp_netdev_flow *flow) { > > > > +int ret = 0; > > > > +uint32_t mark = flow->mark; > > > > +str

Re: [ovs-dev] [PATCH v5 1/5] dpif-netdev: associate flow with a mark id

> -Original Message- > From: Yuanhan Liu [mailto:y...@fridaylinux.org] > Sent: Friday, January 26, 2018 8:20 AM > To: Stokes, Ian > Cc: d...@openvswitch.org; Finn Christensen ; Darrell Ball > ; Chandran, Sugesh ; Simon > Horman > Subject: Re: [PATCH v5 1/5] dpif-netdev: associate flow wit

Re: [ovs-dev] [PATCH] gre: strip gre-tso offload flags

I also it should backport to branch-2.6~2.8 At 2018-01-26 08:16:54, "Gregory Rose" wrote: >On 1/25/2018 10:22 AM, Ben Pfaff wrote: >> On Thu, Jan 25, 2018 at 10:16:23AM -0800, Gregory Rose wrote: >>> On 12/28/2017 8:45 PM, we...@ucloud.cn wrote: From: wenxu if the gro enabl

Re: [ovs-dev] [RFC] netdev-dpdk: Update amount of mbufs requested.

> > -Original Message- > > From: Kevin Traynor [mailto:ktray...@redhat.com] > > Sent: Tuesday, January 23, 2018 6:43 PM > > To: d...@openvswitch.org; Wojciechowicz, RobertX > > ; venkatesan.prad...@ericsson.com; > > jan.scheur...@ericsson.com; Stokes, Ian ; > > i.maxim...@samsung.com; Kavan

[ovs-dev] [PATCH] ovn-nbctl: Add QoS commands.

This patch provides the command line to add/delete/list QoS rule on the logical switch. Signed-off-by: Guoshuai Li --- ovn/utilities/ovn-nbctl.8.xml | 36 +++ ovn/utilities/ovn-nbctl.c | 231 ++ tests/ovn-nbctl.at| 74 ++

Re: [ovs-dev] [PATCH v5 1/5] dpif-netdev: associate flow with a mark id

On Wed, Jan 24, 2018 at 05:29:45PM +, Stokes, Ian wrote: > > Meanwhile, the mark to flow mapping becomes to 1:N mapping. That is what > > Is this 1:N or 1:1? I thought I spotted below that it's 1:1. If you look further, you will also spot "1:N". mark to mega flow is 1:1 mark to flow is 1:N Fo

Re: [ovs-dev] [PATCH branch-2.8 1/1] tc flower: reorder tunnel encap/decap actions

On Thu, Jan 25, 2018 at 03:23:21PM +, John Hurley wrote: > The tc_flower conversion struct does not consider the order of actions. > If an OvS rule matches on a tunnel (decap) and outputs to a new tunnel, > the netlink conversion to TC will add the set tunnel key action before the > unset, lead