Hi Flavio, Daniele
I think that the idea of integrating the patch in the naming convention is
good.
I only have two comments:
- I would keep it limited to physical devices for the moment, maybe in a
future we can think about supporting other device creation arguments.
- How is the detach suppose t
Hello Ciara,
On Fri, Jul 15, 2016 at 11:00 AM, Loftus, Ciara
wrote:
> >
> > Hello Ciara,
> > I like the idea a lot, the restriction on the names has always been a
> limitation,
> > however, it is more important the port id to physical port relation that
> is
> > confusing.
> > I was not able to
Hello Ciara,
I like the idea a lot, the restriction on the names has always been a
limitation, however, it is more important the port id to physical port
relation that is confusing.
I was not able to test the patch, it does not apply and I didn't have the
time to apply it manually.
I have some c
Hi Alex,
This problem usually happens when there is not memory allocated to DPDK in
the socket where the port is connected to. Please use the dpdk-socket-mem
option to set the amount of memory for DPDK in the different NUMA sockets,
Example:
ovs-vsctl --no-wait set Open_vSwitch . other_config:dp
Hello Ciara,
I like too much the idea of arbitrary names, it has always been a problem
realizing the correct id of a port.
As already mentioned by Jan, what do you think about the possibility of
integrate this with hotplug capabilities? I already sent a patch [1] to
support hotplug in ovs-dpdk.
On Thu, Jun 9, 2016 at 4:42 AM, Flavio Leitner wrote:
> On Tue, Jun 07, 2016 at 11:42:11PM +0200, Mauricio Vásquez wrote:
> > On Tue, Jun 7, 2016 at 10:52 PM, Bodireddy, Bhanuprakash <
> > bhanuprakash.bodire...@intel.com> wrote:
> >
> > > Thanks Mauricio f
On Tue, Jun 7, 2016 at 10:52 PM, Bodireddy, Bhanuprakash <
bhanuprakash.bodire...@intel.com> wrote:
> Thanks Mauricio for your comments, My comments inline.
>
> >+ it has to be configured with DPDK support and is done by './configure
> --
> >with-dpdk'.
> >+ This section focus on generic recipe
Hello Bhanuprakash,
few comments inline
On Tue, Jun 7, 2016 at 6:45 PM, Bhanuprakash Bodireddy <
bhanuprakash.bodire...@intel.com> wrote:
> Add INSTALL.DPDK-ADVANCED document that is forked off from original
> INSTALL.DPDK guide. This document is targeted at users looking for
> optimum performanc
Hi Bhanuprakash,
Comments inline.
On Tue, Jun 7, 2016 at 6:45 PM, Bhanuprakash Bodireddy <
bhanuprakash.bodire...@intel.com> wrote:
> Refactor the INSTALL.DPDK in to two documents named INSTALL.DPDK and
> INSTALL.DPDK-ADVANCED. While INSTALL.DPDK document shall facilitate the
> novice user in se
Hi Ben,
On Wed, Jun 1, 2016 at 7:38 PM, Ben Pfaff wrote:
> On Wed, Jun 01, 2016 at 06:48:07PM +0200, Mauricio Vasquez B wrote:
> > when an empty path is given to the --with-dpdk option
> > (--with-dpdk="" or --width-dpdk=$NON_SET_ENV_VARIABLE) the configure
> > script does not show any error and
On Wed, Jun 1, 2016 at 5:14 PM, Bodireddy, Bhanuprakash <
bhanuprakash.bodire...@intel.com> wrote:
> >-Original Message-----
> >From: Mauricio Vásquez [mailto:mauriciovasquezber...@gmail.com]
> >Sent: Wednesday, June 1, 2016 3:37 PM
> >To: Bodireddy, Bhanupraka
On Wed, Jun 1, 2016 at 3:29 PM, Bodireddy, Bhanuprakash <
bhanuprakash.bodire...@intel.com> wrote:
> >-Original Message-----
> >From: Mauricio Vásquez [mailto:mauriciovasquezber...@gmail.com]
> >Sent: Wednesday, June 1, 2016 11:17 AM
> >To: ovs dev
> >Cc:
Dear All,
I noticed that when I run the command
./configure --with-dpdk=$SOME_NON_EXISTING_ENV_VAR
it does not give me an error, somewhere it says:
"checking whether dpdk datapath is enabled... no" but there is not an
explicit error.
I think this behavior should be avoided, an explicit error shou
Hi RobertX,
On Wed, Jun 1, 2016 at 11:26 AM, Wojciechowicz, RobertX <
robertx.wojciechow...@intel.com> wrote:
> Hi Sheroo,
>
> my suggestions inline
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Sheroo
> > Pratap
> > Sent: Wednesday, June 1, 2016
Hi Sheroo,
On Wed, Jun 1, 2016 at 10:47 AM, Sheroo Pratap <
sheroopratapresea...@gmail.com> wrote:
> Hi All,
>
> I am trying to start OVS with DPDK but it is failing with below error.
>
> root@osboxes:/home/osboxes/ovs# ovs-vswitchd unix:$DB_SOCK --pidfile
> --detach
> 2016-06-01T08:25:32Z|
Hi Bhanuprakash,
On Tue, May 24, 2016 at 12:22 PM, Bodireddy, Bhanuprakash <
bhanuprakash.bodire...@intel.com> wrote:
> Thanks Mauricio for the review, my comments inline.
>
>
>
> *From:* Mauricio Vásquez [mailto:mauricio.vasquezber...@studenti.polito.it]
>
> *Sent:*
Hi,
I just sent v6: http://openvswitch.org/pipermail/dev/2016-May/071786.html
On Thu, May 19, 2016 at 9:30 AM, Mauricio Vásquez <
mauricio.vasquezber...@studenti.polito.it> wrote:
>
>
> On Tue, May 17, 2016 at 12:44 AM, Flavio Leitner wrote:
>
>> On Fri, May 13,
On Tue, May 17, 2016 at 4:49 PM, Bhanuprakash Bodireddy <
bhanuprakash.bodire...@intel.com> wrote:
> Add INSTALL.DPDK-ADVANCED document that is forked off from original
> INSTALL.DPDK guide. This document is targeted at users looking for
> optimum performance on OVS using dpdk datapath.
>
> Signed
Hi Bhanuprakash,
Some comments inline.
On Tue, May 17, 2016 at 4:49 PM, Bhanuprakash Bodireddy <
bhanuprakash.bodire...@intel.com> wrote:
> Refactor the INSTALL.DPDK in to two documents named INSTALL.DPDK and
> INSTALL.DPDK-ADVANCED. While INSTALL.DPDK document shall facilitate the
> novice use
mance
> of OVS more accurately and also simplifies the configuration code.
>
> Best regards, Ilya Maximets.
>
> On 20.05.2016 12:23, Mauricio Vásquez wrote:
> > Hello,
> >
> > I noticed that pmd threads are created in a per NUMA node fashion,
> > it means, pmd th
Hello,
I noticed that pmd threads are created in a per NUMA node fashion, it
means, pmd threads are only created in a specific NUMA node when there is a
least one DPDK port on that node.
My concern is that in some cases with this approach more threads than
needed are created, for example, lets su
On Tue, May 17, 2016 at 12:44 AM, Flavio Leitner wrote:
> On Fri, May 13, 2016 at 10:25:41PM +0200, Mauricio Vasquez B wrote:
> > In order to use dpdk ports in ovs they have to be bound to a DPDK
> > compatible driver before ovs is started.
> >
> > This patch adds the possibility to hotplug (or h
On Mon, May 16, 2016 at 7:13 PM, Stokes, Ian wrote:
> > -Original Message-
> > From: Mauricio Vasquez B
> > [mailto:mauricio.vasquezber...@studenti.polito.it]
> > Sent: Friday, May 13, 2016 9:26 PM
> > To: dev@openvswitch.org
> > Cc: acon...@redhat.com; l...@cn.fujitsu.com; mchand...@suse
Hello,
I sent v5: http://openvswitch.org/pipermail/dev/2016-May/070953.html
Mauricio V,
On Wed, May 11, 2016 at 6:53 PM, Mauricio Vásquez <
mauricio.vasquezber...@studenti.polito.it> wrote:
> Hi Flavio,
>
> On Tue, May 10, 2016 at 10:11 PM, Flavio Leitner wrote:
>
>>
Hi Flavio,
On Tue, May 10, 2016 at 10:11 PM, Flavio Leitner wrote:
>
> Thanks for this patch, Mauricio.
> More inline.
>
> On Tue, May 10, 2016 at 09:47:12PM +0200, Mauricio Vásquez wrote:
> > Adding in CC all the people involved.
> > (I don't know why git just t
Adding in CC all the people involved.
(I don't know why git just takes two)
On Tue, May 10, 2016 at 9:11 PM, Mauricio Vasquez B <
mauricio.vasquezber...@studenti.polito.it> wrote:
> In order to use dpdk ports in ovs they have to be bound to a DPDK
> compatible driver before ovs is started.
>
> Th
Hi Markos,
I sent a new version:
http://openvswitch.org/pipermail/dev/2016-May/070795.html
Thank you for your feedback.
On Tue, May 3, 2016 at 5:27 PM, Markos Chandras wrote:
> Hello,
>
> (a couple of minor things I noticed whilst looking at your patch)
> On 04/13/2016 03:08 PM, Mauricio Vasqu
TX-total: 0
>
>
> ++++++++
>
>
>
>
>
> *发件人:* lifuqiong [mailto:lifuqi...@cncloudsec.com]
> *发送时间:* 2016年4月21日 16:22
> *收件人:* 'Mauricio Vásquez'
> *抄送:* 'dev@openvswitch.org'
> *
0:00:00
>
> config: PORT_DOWN
>
> state: LINK_DOWN
>
> speed: 0 Mbps now, 0 Mbps max
>
> LOCAL(ovsbr0): addr:2c:53:4a:01:cd:5e
>
> config: 0
>
> state: 0
>
> current:10MB-FD COPPER
>
> speed: 10 Mb
, bytes=0, drop=0, errs=0, coll=?
>
> port 2: rx pkts=0, bytes=0, drop=0, errs=0, frame=?, over=?, crc=?
>
>tx pkts=0, bytes=0, drop=0, errs=0, coll=?
>
> port 3: rx pkts=1919, bytes=184174, drop=?, errs=0, frame=?, over=?,
> crc=?
>
>tx pkts=
3 0 00:00:00:00:00:041
>
>
>
>
>
> What was the reason why VM cannot communication with the PC? Thank you
>
>
>
> *发件人:* lifuqiong [mailto:lifuqi...@cncloudsec.com]
> *发送时间:* 2016年4月15日 9:22
> *收件人:* 'Mauricio Vásquez'
> *抄送:* 'dev@
Now it is clear for me,
Thanks Ben.
On Fri, Apr 15, 2016 at 6:47 PM, Ben Pfaff wrote:
> On Fri, Apr 15, 2016 at 03:11:42PM +0200, Mauricio Vásquez wrote:
> > I would like to know how is the methodology to back-port bug fixes in
> ovs,
> > I ask it because with [1] I notice
Dear All,
I would like to know how is the methodology to back-port bug fixes in ovs,
I ask it because with [1] I noticed that this bug is fixed on branch-2.5
but there is not any stable release that contains the fix.
[1] http://openvswitch.org/pipermail/dev/2016-April/069579.html
Thanks in advan
Hello lifuqiong,
I faced the same problem some days ago (
http://openvswitch.org/pipermail/dev/2016-March/068282.html), the bug is
already fixed.
Where are you downloading OVS from?, it appears that the bug is still
present in the version on
http://openvswitch.org/releases/openvswitch-2.5.0.tar.gz
Hello Li,
On Fri, Apr 1, 2016 at 11:08 AM, Li Wei wrote:
> Hello,
>
> On 03/28/2016 04:52 PM, Mauricio Vasquez B wrote:
> > In order to use dpdk ports in ovs they have to be bound to a DPDK
> > compatible driver before ovs is started.
> >
> > This patch adds the possibility to hotplug (o
Hi Ian,
On Thu, Mar 31, 2016 at 2:02 PM, Stokes, Ian wrote:
> Hi Mauricio,
>
> This patch is quite useful. Some minor comments inline. I've also tested
> the patch and can confirm it works without issue.
>
Great!
>
> Thanks
> Ian
>
> > -Original Message-
> > From: dev [mailto:dev-boun
Right, I'll wait for a review and then I'll send a V2 with all the patches
in one.
On Mon, Mar 28, 2016 at 11:43 PM, Justin Pettit wrote:
>
> > On Mar 28, 2016, at 1:52 AM, Mauricio Vasquez B <
> mauricio.vasquezber...@studenti.polito.it> wrote:
> >
> > Signed-off-by: Mauricio Vasquez B <
> maur
I sent a proper patch:
http://openvswitch.org/pipermail/dev/2016-March/068600.html
On Thu, Mar 24, 2016 at 11:57 AM, Mauricio Vásquez <
mauricio.vasquezber...@studenti.polito.it> wrote:
> Hi Aaron,
>
> First of all thank you very much for your feedback.
>
> I didn't
On Fri, Mar 25, 2016 at 7:50 AM, Ilya Maximets
wrote:
> According to QEMU documentation (docs/specs/vhost-user.txt) one queue
> should be enabled initially. More queues are enabled dynamically, by
> sending message VHOST_USER_SET_VRING_ENABLE.
>
> Currently all queues in OVS disabled by default.
Chandras wrote:
> On 03/24/2016 02:32 PM, Mauricio Vásquez wrote:
> > Hi Markos,
> >
> > Currently DPDK 2.2.0 is required to build OVS master, DPDK 2.2.0 still
> > requires setting the CONFIG_RTE_BUILD_COMBINE_LIBS option.
> >
> > I think we need to wait
Hi Markos,
Currently DPDK 2.2.0 is required to build OVS master, DPDK 2.2.0 still
requires setting the CONFIG_RTE_BUILD_COMBINE_LIBS option.
I think we need to wait until we move to a new DPDK version to change the
documentation.
Mauricio V,
On Thu, Mar 24, 2016 at 2:13 PM, Markos Chandras wro
Hi Aaron,
First of all thank you very much for your feedback.
I didn't pay that attention to the style, I'll correct all the issues when
I send a proper patch, by the way, is there any script or tool to check the
style?, I looked for it and I cannot find anything.
On Wed, Mar 23, 2016 at 11:42 A
, Mar 23, 2016 at 10:21 AM, Ilya Maximets
wrote:
> On 23.03.2016 12:19, Mauricio Vásquez wrote:
> > Hi IIya,
> >
> > I'm using DPDK 2.2.0 and QEMU 2.2.1.
>
> You should use QEMU 2.5.
>
> > On Wed, Mar 23, 2016 at 10:18 AM, Ilya Maximets <mailto:i.ma
Hi IIya,
I'm using DPDK 2.2.0 and QEMU 2.2.1.
On Wed, Mar 23, 2016 at 10:18 AM, Ilya Maximets
wrote:
> What version of DPDK and QEMU you're using with OVS 2.5?
>
> On 23.03.2016 12:11, Mauricio Vásquez wrote:
> > Dear all,
> >
> > I am testing a setup wh
Somebody wants to have at look at this?
Thanks,
On Wed, Mar 16, 2016 at 3:40 PM, Mauricio Vasquez B <
mauricio.vasquezber...@studenti.polito.it> wrote:
> In order to use dpdk ports in ovs they have to be bound to a DPDK
> compatible driver before ovs is started.
>
> This patch adds the possibilit
Dear all,
I am testing a setup where two VMs have to communicate using vhost-user
ports, it works using OvS 2.4 but it does not work with the master version
nor with 2.5.
The setup is quite simple, a pair of VMs connected to OvS using vhost-user
ports, two flows configured to forward the packets
Hi Daniele,
I didn't know about that function, thanks!.
I already sent the new versions:
http://openvswitch.org/pipermail/dev/2016-February/066650.html
http://openvswitch.org/pipermail/dev/2016-February/066649.html
Thank you very much!.
On 23 February 2016 at 19:12, Daniele Di Proietto
wrote:
Dear All,
I think this change should be announce in the NEWS file, Shouldn't it?
Thanks,
On 25 January 2016 at 21:53, Daniele Di Proietto
wrote:
> Apologies for the delay.
>
> I applied this to master and branch-2.5 with the following incremental,
> to remove a deprecation warning:
>
> diff --
On 25 January 2016 at 10:42, Aaron Conole wrote:
> Mauricio Vasquez B writes:
>
> > Current implementation allows to support only until the dpdkr255 port,
> > this patch extends it to support the full range of possible dpdkr ports.
>
> I think this commit message is not correct. This patch just
Hello Aaron,
On 25 January 2016 at 10:28, Aaron Conole wrote:
> Mauricio Vasquez B writes:
>
> > Current implementation of dpdk_dev_parse_name does not perform a robust
> > error handling, port names as "dpdkr" or "dpdkr1x" are considered valid.
>
> Mauricio, thanks for the patch!
>
> > Signed-
I sent this patch as part of a patch series:
http://openvswitch.org/pipermail/dev/2016-January/064968.html.
Thank you very much.
On 15 January 2016 at 10:17, Traynor, Kevin wrote:
>
> > -Original Message-
> > From: Mauricio Vásquez [mailto:mauricio.vasquezber...@stu
Hello Kevin,
It can only work up to 255 actually, notice that the port number is
first parsed and saved in the variable "uint8_t client_id", then the
type of this variable should be changed too. Additionally, the port
number in ovs is saved in the member "int user_port_id;" of the
dpdk_ring struct
Dear Aaron,
I completely agree with you, I've sent a second version:
http://openvswitch.org/pipermail/dev/2016-January/064228.html
Thank you very much,
Mauricio Vasquez B
On 10 January 2016 at 12:17, Aaron Conole wrote:
> Greetings Mauricio,
>
> Mauricio Vasquez B writes:
> > A ring name leng
Hello Furong,
Unfortunately it is not well documented, I'm going to explain what you need
to start:
- The ivshmem mechanism of DPDK does not work with a standard version of
QEMU, then you need a patched version. It could be found at the dpdk-ovs
project: https://github.com/01org/dpdk-ovs.
You can
December 2015 at 09:20, Mauricio Vásquez <
mauricio.vasquezber...@studenti.polito.it> wrote:
> I updated to the last git version and then applied your patch. The issue
> is still present.
>
> The ovs log still shows the message
> "2015-12-31T14:18:04Z|1|dpif_netdev(pmd
e.
> Please try my new patch "[PATCH RFC] dpif-netdev: Rework of rx queue
> management."
> http://openvswitch.org/pipermail/dev/2015-December/063920.html
>
> May be it will help.
>
> Best regards, Ilya Maximets.
>
> On 30.12.2015 18:25, Mauricio Vásquez wrote:
> &
pmd_thread *pmd;
> -
> -CMAP_FOR_EACH (pmd, node, &dp->poll_threads) {
> -dp_netdev_reload_pmd__(pmd);
> -}
> +dp_netdev_destroy_all_pmds(dp);
> +dp_netdev_set_nonpmd(dp);
> +dp_netdev_reset_pmd_threads(dp);
> }
>
> static uint32_t
> ---
>
> I'll try to
packet: 18642.59 (37229257/1997)
avg processing cycles per packet: 15023.85 (30002635/1997)
Other threads continue to show a high number of miss packets, throughput is
still 700 kpps.
On 30 December 2015 at 09:36, Ilya Maximets wrote:
> On 30.12.2015 17:32, Mauricio Vásquez wrote:
&g
I just checked and the traffic is generated after everything is already set
up, ports and flows.
On 30 December 2015 at 08:50, Ilya Maximets wrote:
> The transmission starts before the addition of dpdkr4 to ovs?
>
> On 30.12.2015 16:31, Mauricio Vásquez wrote:
> > Dear Il
08:05, Ilya Maximets wrote:
> On 30.12.2015 15:51, Mauricio Vásquez wrote:
> > Hello Ilya,
> >
> > The dpdkr ports involved have just one TX queue, so it should not be the
> reason in this case.
> >
>
> Please, provide output of:
> ovs-appctl dpif-netde
eues. That's why most of pmd threads can't install a ukey
> and always executes a misses instead of emc hits.
>
> Fix your 'Source'.
>
> Best regards, Ilya Maximets.
>
> On 29.12.2015 22:19, Mauricio Vásquez wrote:
> > Hello to all,
> >
>
Hello to all,
I am performing some performance testing using OVS with DPDK and I am
having some issues when I change the number of PMD cores that ovs uses.
The testing architecture consists of a source and sink processes, the
source allocates some packets from the memory pool at the beginning and
Dear Aaron,
The general idea looks good to me.
Just some comments inline
On 3 December 2015 at 05:23, Aaron Conole wrote:
> Existing DPDK integration is provided by use of command line options which
> must be split out and passed to librte in a special manner. However, this
> forces any confi
Dear Ben,
You are right, now it works.
Thank you very much!
On 20 November 2015 at 18:48, Ben Pfaff wrote:
> On Fri, Nov 20, 2015 at 05:39:37PM +0100, Mauricio Vásquez wrote:
> > Dear all,
> > according to [1] by default ovs inserts some hidden flows that can create
> >
Dear all,
according to [1] by default ovs inserts some hidden flows that can create
loops in particular conditions.
I am experiencing the same problem using ovs with the DPDK datapath and
then, after configuring the controller through the command
ovs-vsct --no-wait set-controller br0 tcp:127.0.0.
I have sent a new patch modifying the commit title and commit message:
http://openvswitch.org/pipermail/dev/2015-November/062257.html
Mauricio V,
On 16 November 2015 at 19:39, Flavio Leitner wrote:
> On Mon, Nov 16, 2015 at 11:25:11AM +0100, Mauricio Vásquez wrote:
> > On 16 Novembe
On 16 November 2015 at 06:48, Flavio Leitner wrote:
> On Wed, Nov 11, 2015 at 09:22:39AM +0100, Mauricio Vásquez wrote:
>
> The commit title can be more clear like
> "netdev-dpdk: assume dpdr peer can be multi-producer/consumer"
>
I agree, you just missed a letter,
&
Although netdev does explicit locking, it is only valid from the ovs
perspective, then only the ring ends used by ovs should be declared as
single producer / single consumer.
The other ends that are used by the application should be declared as
multiple producer / multiple consumer that is the mos
Right now I realized that I did not respect the 79 characters width limit
on
the description.
Should I resend the path?
Thank you very much.
On 10 November 2015 at 23:42, Mauricio Vásquez <
mauricio.vasquezber...@studenti.polito.it> wrote:
> Although netdev does explicit locking, i
Although netdev does explicit locking, it is only valid from the ovs
perspective, then only the ring ends used by ovs should be declared as
single producer / single consumer.
The other ends that are used by the application should be declared as
multiple producer / multiple consumer that is the most
The openvswitch directory does not exist anymore, boot.sh and configure are
located at $(OVS_DIR).
Signed-off-by: Mauricio Vasquez B
---
INSTALL.DPDK.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/INSTALL.DPDK.md b/INSTALL.DPDK.md
index 7bf110c..02588c4 100644
--- a/INST
The definition of the INIT_CONTAINER macro initializes ITER to NULL,
it will cause a segmentation fault when it is deferenced on
(ITER)->MEMBER.next, then, I changed it to the ASSIGN_CONTAINER macro that
does not initialize ITER.
Signed-off-by: Mauricio Vasquez B
---
lib/list.h | 2 +-
1 file c
On Mon, May 18, 2015 at 7:09 PM, Traynor, Kevin
wrote:
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Mauricio
> Vásquez
> > Sent: Monday, May 18, 2015 9:31 AM
> > To: dev@openvswitch.org; ivano cerrato
> > S
I'm performing a series of VM2VM communication testing where a virtual
machine is a packet generator while the other one just receives all the
packets.
When I tested dpdk-ovs[1] I used a port type called dpdkclient: this port
has 4 rings, (tx, rx, alloc_q and free_q), alloc_q and free_q are used
b
74 matches
Mail list logo
