The zone Netlink attribute is supposed to be in network-byte order, but
the Windows code for deleting conntrack entries was treating it as
host-byte order.
Found by inspection.
Signed-off-by: Justin Pettit
---
datapath-windows/ovsext/Conntrack.c | 2 +-
lib/netlink-conntrack.c | 2 +
From: wangzhike
ICMP response (Unreachable/fragmentationRequired/...) may be created
at devices in the middle, and such packets are tagged as invalid in
user space conntrack. In fact it does not make sense to validate the
src and dest address.
Signed-off-by: wang zhike
---
lib/conntrack.c | 13
Confidential Request
Attn: Sir/Madam,
My family have an urgent inheritance fund of US$15 Million that we would like
to invest with you. We are looking for a reliable and capable foreign partner
that will assist my family and I to receive
Hi Ilya,
I have retested your "Output patches batching" v6 in our standard PVP
L3-VPN/VXLAN benchmark setup [1]. The configuration is a single PMD serving a
physical 10G port and a VM running DPDK testpmd as IP reflector with 4 equally
loaded vhostuser ports. The tests are run with 64 byte pa
> We can't change the name of the "protected" column in the database
> schema, because that breaks backward compatibility. Another approach
> would be to make ovsdb-idlc use a different name for columns whose names
> are C or C++ keywords; for example, it could append an underscore.
Hi Ben,
Than
In C++, 'protected' is a keyword. This patch renames 'protected'
to 'protected_' in a couple files so that C++ compiler will
not get confused.
Signed-off-by: Yi-Hung Wei
---
ofproto/ofproto-dpif.c | 10 +-
ofproto/ofproto.h | 2 +-
ovsdb/ovsdb-idlc.1 | 6 --
ovsdb/ovsdb-id
>On Mon, Dec 04, 2017 at 08:16:48PM +, Bhanuprakash Bodireddy wrote:
>> With ovs_prefetch_range(), large amounts of data can be prefetched in
>> to caches. Prefetch type gives better control over data caching
>> strategy; Meaning where the data should be prefetched(L1/L2/L3) and if
>> the data
On Mon, Dec 04, 2017 at 08:59:47PM +, Bodireddy, Bhanuprakash wrote:
> >On Mon, Dec 04, 2017 at 08:16:47PM +, Bhanuprakash Bodireddy wrote:
> >> Processors support prefetch instruction in anticipation of write but
> >> compilers(gcc) won't use them unless explicitly asked to do so even
> >>
>On Mon, Dec 04, 2017 at 08:16:47PM +, Bhanuprakash Bodireddy wrote:
>> Processors support prefetch instruction in anticipation of write but
>> compilers(gcc) won't use them unless explicitly asked to do so even
>> with '-march=native' specified.
>>
>> [Problem]
>> Case A:
>> OVS_PREFETCH
Hi Ben,
>On Mon, Dec 04, 2017 at 08:16:46PM +, Bhanuprakash Bodireddy wrote:
>> This commit introduces prefetch variants by using the GCC built-in
>> prefetch function.
>>
>> The prefetch variants gives the user better control on designing data
>> caching strategy in order to increase cache ef
On Mon, Dec 04, 2017 at 08:16:48PM +, Bhanuprakash Bodireddy wrote:
> With ovs_prefetch_range(), large amounts of data can be prefetched in to
> caches. Prefetch type gives better control over data caching strategy;
> Meaning where the data should be prefetched(L1/L2/L3) and if the data
> refer
On Mon, Dec 04, 2017 at 08:16:47PM +, Bhanuprakash Bodireddy wrote:
> Processors support prefetch instruction in anticipation of write but
> compilers(gcc) won't use them unless explicitly asked to do so even
> with '-march=native' specified.
>
> [Problem]
> Case A:
> OVS_PREFETCH_CACHE(
> > Found while running tests on branch-2.8.
> >
> > Signed-off-by: Alin Gabriel Serdean
>
> I did not apply the patch and run the tests myself, but this seems like an
> obvious fix. Thank you.
>
> Acked-by: Ben Pfaff
Thanks for the quick review. I applied it on branch-2.8.
__
On Mon, Dec 04, 2017 at 08:16:46PM +, Bhanuprakash Bodireddy wrote:
> This commit introduces prefetch variants by using the GCC built-in
> prefetch function.
>
> The prefetch variants gives the user better control on designing data
> caching strategy in order to increase cache efficiency and m
Prefetch the cacheline having the cycle stats so that we can speed up
the cycles_count_start() and cycles_count_intermediate().
Signed-off-by: Bhanuprakash Bodireddy
---
lib/dpif-netdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
OVS_PREFETCH by default uses OPCH_HTR(High Temporal Read), meaning
the prefetch is in preparation for a future read and the prefetched
data is made available in all levels of caches.
However the pkt_metadata_prefetch_init() prefetches the metadata so that
the data is readily available when pkt_met
With ovs_prefetch_range(), large amounts of data can be prefetched in to
caches. Prefetch type gives better control over data caching strategy;
Meaning where the data should be prefetched(L1/L2/L3) and if the data
reference is temporal or non-temporal.
Signed-off-by: Bhanuprakash Bodireddy
---
l
Processors support prefetch instruction in anticipation of write but
compilers(gcc) won't use them unless explicitly asked to do so even
with '-march=native' specified.
[Problem]
Case A:
OVS_PREFETCH_CACHE(addr, OPCH_HTW)
__builtin_prefetch(addr, 1, 3)
leaq-112(%rbp), %ra
This commit introduces prefetch variants by using the GCC built-in
prefetch function.
The prefetch variants gives the user better control on designing data
caching strategy in order to increase cache efficiency and minimize
cache pollution. Data reference patterns here can be classified in to
-
pkt_metadata_prefetch_init() is used to prefetch the packet metadata
before initializing the metadata in pkt_metadata_init(). This is done
for every packet in userspace datapath and is performance critical.
Commit 99fc16c0 prefetches only cachline0 and cacheline2 as the metadata
part of respective
On Tue, Nov 28, 2017 at 04:09:25PM -0800, Ben Pfaff wrote:
> The 'mask' buffer in parse_odp_action() is supposed to always be big
> enough:
> /* 'mask' is big enough to hold any key. */
>
> Geneve options can be really big and the comment was wrong. This commit
> fixes the problem.
>
> F
The 'mask' buffer in parse_odp_action() is supposed to always be big
enough:
/* 'mask' is big enough to hold any key. */
Geneve options can be really big and the comment was wrong. In addition,
the user might supply more options than can really fit in any case, so
we might as well just us
Lots to digest - responses below
Jan Scheurich writes:
> Hi Darrel,
> Let me try respond to your points below.
> Regards, Jan
>> -Original Message-
>> From: Darrell Ball [mailto:db...@vmware.com]
>> Sent: Thursday, 30 November, 2017 01:33
>>
>> The idea of creating an “Conntrack Establi
On Mon, Dec 04, 2017 at 08:47:38AM +, Vishal Deep Ajmera wrote:
> As per OpenFlow v1.3 specification, when an action list contains a group
> action a copy of the packet is passed to the group for processing by the
> group. This means that if there is an error encountered during group
> processi
Applied, thanks.
On Mon, Dec 04, 2017 at 03:06:39PM +0100, Daniel Alvarez Sanchez wrote:
> Acked-by: Daniel Alvarez
>
> From [0] one can expect this column to be present in all tables.
> [0] https://github.com/openvswitch/ovs/blob/v2.8.1/ovn/ovn-nb.xml#L19
>
> On Mon, Dec 4, 2017 at 2:16 PM, w
This patch is a simple implementation for the proposal discussed in
https://mail.openvswitch.org/pipermail/ovs-dev/2017-August/337038.html and
https://mail.openvswitch.org/pipermail/ovs-dev/2017-October/340013.html.
It enables ovs-vswitchd to use DNS names when specifying OpenFlow and
OVSDB remote
On Mon, Dec 04, 2017 at 10:14:31AM -0800, Gregory Rose wrote:
> On 12/4/2017 9:45 AM, Ben Pfaff wrote:
> >On Mon, Dec 04, 2017 at 09:00:56AM -0800, Gregory Rose wrote:
> >>On 11/18/2017 2:01 AM, w00273186 wrote:
> >>>From: Yunjian Wang
> >>>
> >>>The variable tun_dst in struct ovs_gso_cb isn't nec
On 12/4/2017 9:45 AM, Ben Pfaff wrote:
On Mon, Dec 04, 2017 at 09:00:56AM -0800, Gregory Rose wrote:
On 11/18/2017 2:01 AM, w00273186 wrote:
From: Yunjian Wang
The variable tun_dst in struct ovs_gso_cb isn't necessarily all-zeros which
came from the Netlink layer. When delete a netdev port an
Todo lo que necesita saber para negociar los términos de relaciones laborales
Taller práctico de finiquitos y liquidaciones
08 de Diciembre - MCE. Abdón Guzmán - 9am-3pm
Cuando no se cuenta con los conocimientos de derecho laboral y fiscal, así como
las formas y procedimientos sólidos para term
Hi,
This was one of the items discussed in the last OVS-DPDK public meeting
(29-Nov). Considering that this change is passive (disabled by default and does
not come in fast-path) and makes OVS (when enabled) more secure for potential
DOS-attack, could this be considered for OVS 2.9?
In any cas
On Mon, Dec 04, 2017 at 09:00:56AM -0800, Gregory Rose wrote:
> On 11/18/2017 2:01 AM, w00273186 wrote:
> >From: Yunjian Wang
> >
> >The variable tun_dst in struct ovs_gso_cb isn't necessarily all-zeros which
> >came from the Netlink layer. When delete a netdev port and immediately add
> >a vxlan
On Sun, Dec 03, 2017 at 08:09:02PM +0200, Alin Gabriel Serdean wrote:
> The tests:
> ofproto-dpif - conntrack - controller
> ofproto-dpif - conntrack - force commit
> ofproto-dpif - conntrack - recirc,commit
>
> are broken on branch-2.8, because they are missing "ip," in the receive
> packet.
>
On 11/18/2017 2:01 AM, w00273186 wrote:
From: Yunjian Wang
The variable tun_dst in struct ovs_gso_cb isn't necessarily all-zeros which
came from the Netlink layer. When delete a netdev port and immediately add
a vxlan port, they maybe use the same port_no. So the variable tun_dst of
struct ovs_
On Mon, Dec 04, 2017 at 08:32:28AM -0800, Gregory Rose wrote:
> On 11/30/2017 10:38 AM, Ben Pfaff wrote:
> >Reported-by: Shivaram Mysore
> >Signed-off-by: Ben Pfaff
> >---
> > Documentation/howto/sflow.rst | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> >diff --git a/Documentatio
On 12/3/2017 8:51 PM, Ben Pfaff wrote:
I'm the wrong one to review it, I don't know the datapath well enough
anymore.
Perhaps Greg could take a look.
I'll have a look at it today.
Thanks,
- Greg
On Mon, Dec 04, 2017 at 01:36:52AM +, wangyunjian wrote:
Can we review this patch? It's b
On Mon, Dec 04, 2017 at 10:26:13AM -0200, Flavio Leitner wrote:
> On Fri, 1 Dec 2017 11:22:59 -0800
> Ben Pfaff wrote:
> > The coding style has never been explicit about this. This commit adds some
> > explanation of why one position or the other might be favored in a given
> > situation.
> >
>
On Fri, Dec 01, 2017 at 11:41:12PM +, Tiago Lam wrote:
> Thanks, Ben!
>
> This clarifies things for me. I've also tried to render the file and
> everything looks fine.
>
> Only one small nit below, but it doesn't affect the rendering, thus, for
> what it's worth:
>
> Acked-by: Tiago Lam
>
On 11/30/2017 10:38 AM, Ben Pfaff wrote:
Reported-by: Shivaram Mysore
Signed-off-by: Ben Pfaff
---
Documentation/howto/sflow.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/howto/sflow.rst b/Documentation/howto/sflow.rst
index 1152a7db567a..66f4856b3340
On 11/30/17, 8:02 AM, "Aaron Conole" wrote:
Darrell Ball writes:
> There is a bug here in that the control connection should still be
created even though it is likely an unused control connection.
> The following incremental fixes it.
Good catch. While thinking abou
Presently, alg processing is enabled by default to better exercise code.
This is similar to kernels before 4.7 as well. The recommended default
behavior in the newer kernels is to only process algs if a helper is
supplied in a conntrack rule. The behavior is changed to match the
later kernels.
A
Algs can use variable control port numbers for servers.
The main use case is a kind of feeble security measure; the
thinking being by some is that it obscures the alg traffic.
It is really not very effective, but the kernel has this
capability. This patch mimics the capability.
Signed-off-by: Darr
Some refactoring of alg support is done.
Also allow for non-standard alg conntrol port specification.
Also algs are now disabled by default, unless an alg specifier
is supplied; this allows for enhanced security and matches
later kernels.
v2->v3: 1/ A bit more refactoring for patch 1.
2/ F
Upcoming requirements for new algs make it desirable to split out
alg helpers more cleanly.
Signed-off-by: Darrell Ball
---
lib/conntrack.c | 156
1 file changed, 101 insertions(+), 55 deletions(-)
diff --git a/lib/conntrack.c b/lib/connt
On Mon, Dec 4, 2017 at 7:39 PM, Numan Siddique wrote:
>
>
> On Mon, Dec 4, 2017 at 7:12 PM, Russell Bryant wrote:
>
>> On Mon, Dec 4, 2017 at 12:29 AM, wrote:
>> > From: Numan Siddique
>> >
>> > Pacemaker Resource agent periodically calls the OVN OCF's "monitor"
>> action
>> > periodically to
From: Numan Siddique
Pacemaker Resource agent periodically calls the OVN OCF's "monitor" action
periodically to check the status. But the OVN OCF script doesn't add the
action "monitor" for the role "Master" because of which the pacemaker
resource agent do not call the "monitor" action at all for
On Mon, Dec 4, 2017 at 7:12 PM, Russell Bryant wrote:
> On Mon, Dec 4, 2017 at 12:29 AM, wrote:
> > From: Numan Siddique
> >
> > Pacemaker Resource agent periodically calls the OVN OCF's "monitor"
> action
> > periodically to check the status. But the OVN OCF script doesn't add the
> > action
On Mon, 4 Dec 2017 11:44:19 -0200, Flavio Leitner wrote:
> It is only positive numbers if you review the kernel sources today,
> but the API is exposing signed 32bit, so not sure what can happen
> in the future if the kernel decides to expand the range.
I think you can assume that it will always b
Acked-by: Daniel Alvarez
>From [0] one can expect this column to be present in all tables.
[0] https://github.com/openvswitch/ovs/blob/v2.8.1/ovn/ovn-nb.xml#L19
On Mon, Dec 4, 2017 at 2:16 PM, wrote:
> From: Lucas Alvares Gomes
>
> The external_ids column is missing from the NAT and
> Logical
Acked-by: Miguel Angel Ajo
On Mon, Dec 4, 2017 at 2:16 PM, wrote:
> From: Lucas Alvares Gomes
>
> The external_ids column is missing from the NAT and
> Logical_Router_Static_Route tables.
>
> Signed-off-by: Lucas Alvares Gomes
> ---
> ovn/ovn-nb.ovsschema | 14 ++
> ovn/ovn-nb.xm
On Fri, 1 Dec 2017 13:15:06 -0800
Ben Pfaff wrote:
> On Thu, Nov 09, 2017 at 03:31:01PM -0200, Flavio Leitner wrote:
> > A port might be already in another netns, so initialize it
> > as invalid to force a state update.
> >
> > Signed-off-by: Flavio Leitner
>
> This doesn't build for me:
>
Hello,
I tested it.
It is ok for my meter patch:
https://mail.openvswitch.org/pipermail/ovs-dev/2017-December/341544.html
This commit adds support for DPDK v17.11:
- minor updates to accomodate DPDK API changes
- update references to DPDK version in Documentation
- update DPDK version in travis
On Tue, 14 Nov 2017 10:55:44 -0800
Gregory Rose wrote:
> On 11/9/2017 9:31 AM, Flavio Leitner wrote:
> > Recent kernels provide the network namespace ID of a port,
> > so use that to discover where the port currently is.
> >
> > Signed-off-by: Flavio Leitner
> > ---
> > datapath/linux/compat/i
On Fri, 1 Dec 2017 13:14:07 -0800
Ben Pfaff wrote:
> On Thu, Nov 09, 2017 at 03:31:00PM -0200, Flavio Leitner wrote:
> > The netlink notification's ancillary data contains the network
> > namespace id (netnsid) needed to identify the device correctly.
> > (ifindex and netnsid).
> >
> > Signed-of
On Mon, Dec 4, 2017 at 12:29 AM, wrote:
> From: Numan Siddique
>
> Pacemaker Resource agent periodically calls the OVN OCF's "monitor" action
> periodically to check the status. But the OVN OCF script doesn't add the
> action "monitor" for the role "Master" because of which the pacemaker
> resou
From: Lucas Alvares Gomes
The external_ids column is missing from the NAT and
Logical_Router_Static_Route tables.
Signed-off-by: Lucas Alvares Gomes
---
ovn/ovn-nb.ovsschema | 14 ++
ovn/ovn-nb.xml | 14 ++
2 files changed, 24 insertions(+), 4 deletions(-)
diff -
On Fri, 1 Dec 2017 11:22:59 -0800
Ben Pfaff wrote:
> The coding style has never been explicit about this. This commit adds some
> explanation of why one position or the other might be favored in a given
> situation.
>
> Suggested-by: Flavio Leitner
> Suggested-at:
> https://mail.openvswitch.o
This commit adds support for DPDK v17.11:
- minor updates to accomodate DPDK API changes
- update references to DPDK version in Documentation
- update DPDK version in travis' linux-build script
Signed-off-by: Mark Kavanagh
Acked-by: Maxime Coquelin
Acked-by: Ciara Loftus
---
.travis/linux-buil
DPDK v17.11 introduces support for the vHost IOMMU feature.
This is a security feature, which restricts the vhost memory
that a virtio device may access.
This feature also enables the vhost REPLY_ACK protocol, the
implementation of which is known to work in newer versions of
QEMU (i.e. v2.10.0), b
This patchset adds support for DPDK v17.11:
- the first patch introduces minor code updates to accomodate DPDK API
changes, and also updates Documentation and travis scripts.
- the second patch adds a new global configuration option,
vhost-iommu-support; this is required in order to take advant
>From: Ilya Maximets [mailto:i.maxim...@samsung.com]
>Sent: Friday, December 1, 2017 5:34 AM
>To: Kavanagh, Mark B ; d...@openvswitch.org
>Cc: ktray...@redhat.com; maxime.coque...@redhat.com;
>jan.scheur...@ericsson.com; Mooney, Sean K ; Stokes,
>Ian
>Subject: Re: [ovs-dev][PATCH V3 0/2] DPDK v17.
Saludos de la Sra. Gloria Febian
Me pongo en contacto con usted en base a sus buenos perfiles que leo. Y por
buenas razones, estoy en busca de una propiedad para comprar en su país, ya que
tenía la intención de venir a su país para la inversión. Aunque no me he
encontrado con usted antes, pero
Hi Business Owners,
I amvirendra singh pal, and I work with experienced IT professionals who
specializein the following services.
1. Website Designing
2. Web Development
3. Responsive Websites
4. PHP Development
5. E-Commerce Solutions
6. Magento Website Development
May I kn
As per OpenFlow v1.3 specification, when an action list contains a group
action a copy of the packet is passed to the group for processing by the
group. This means that if there is an error encountered during group
processing, only the copy of packet should be dropped, but subsequent
actions in the
Hello Ben:
I have sent a new patch serial, based on your review comments:
https://mail.openvswitch.org/pipermail/ovs-dev/2017-December/341543.html
https://mail.openvswitch.org/pipermail/ovs-dev/2017-December/341544.html
Thanks,
Guoshuai
On Mon, Nov 13, 2017 at 08:23:29PM +0800, Guoshuai Li
This feature is used to limit the bandwidth of flows, such as floating IP.
ovn-northd changes:
1. add bandwidth column in NB's QOS table.
2. add QOS_METER stages in Logical switch ingress/egress.
3. add set_meter() action in SB's LFlow table.
ovn-controller changes:
add meter_table for meter acti
The structure and function of the group table and meter table are similar,
refactoring code is used to extend for add the meter table.
The following function as lib: table init/destroy/clear,
install contents from desired, remove contents from existing,
Move the contents of desired to existing.
Si
66 matches
Mail list logo
