I just wanted to specially call out this patch for testing. My hope is that we
can merge this into 2.8, but wanted to give people a heads up that they may
want to try it with their applications. The most visible change is that a call
to ct() will clear the ct_state for any actions that follow
Packet and Connection state is only available to the processing path
that follows the "recirc_table" argument of the ct() action. The
previous behavior made these states available until the end of the
pipeline. This commit changes the behavior so that the Packet and
Connection state are cleared f
From: ovs-dev-boun...@openvswitch.org on
behalf of Anand Kumar
Sent: Thursday, August 10, 2017 8:59 PM
To: d...@openvswitch.org
Subject: [ovs-dev] [PATCH] datapath-windows: Do not modify port field for
ICMP during SNAT/DNAT
During SNAT/DNAT, we s
During SNAT/DNAT, we should not be updating the port field of ct_endpoint
struct, as ICMP packets do not have port information. Since port and
icmp_id are overlapped in ct_endpoint struct, icmp_id gets changed.
As a result, NAT look up fails to find a matching entry.
This patch addresses this issu
On Thu, Aug 10, 2017 at 02:31:43PM -0700, Joe Stringer wrote:
> On 10 August 2017 at 11:41, Ben Pfaff wrote:
> > On Thu, Aug 10, 2017 at 01:01:32PM +0800, Gao Zhenyu wrote:
> >> Besides of that, I see many places consume the table class.
> >> Do you mind to make a macro helps to fetch the class?
>
Hello, I encounter a problem with running ovs with IVSHMEM.
I've followed the guide of INSTALL.DPDK.md of ovs-2.5.0 to use IVSHMEM.
Firstly, I started ovs-vswitchd using "./sbin/ovs-vswitchd --dpdk -c 0x1
-n 4 --proc-type=primary -- --pidfile --detach", and I added dpdk
ports(dpdk0,dpdk1) and d
Hi Bhanu
Given that you ultimately intend changes beyond those in this patch, would it
make sense
just to fold the follow up series (at least, the key elements) into this
series, essentially expanding
on this patch 5 ?
Thanks Darrell
-Original Message-
From: on behalf of Bhanuprakash
Hi All
As discussed in the fortnightly DPDK meeting, I am using a repo for DPDK patch
merging.
The repo is here: https://github.com/darball/ovs/
Branch is dpdk_merge - based on ovs master.
Nothing for this week, as reviews are not completed yet for some features.
Thanks Darrell
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Rxqs consumed processing cycles are used to improve the balance
of how rxqs are assigned to pmds. Currently some reconfiguration
is needed to perform a reassignment.
Add an ovs-appctl command to perform a new assignment in order
to balance based on th
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Up to his point rxqs are sorted by processing cycles they
consumed and assigned to pmds in a round robin manner.
Ian pointed out that on wrap around the most loaded pmd will be
the next one to be assigned an additional rxq and that it would be
better
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Previously rxqs were assigned to pmds by round robin in
port/queue order.
Now that we have the processing cycles used for existing rxqs,
use that information to try and produced a better balanced
distribution of rxqs across pmds. i.e. given multiple p
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Count the cycles used for processing an rxq during the
pmd rxq interval. As this is an in flight counter and
pmds run independently, also store the total cycles used
during the last full interval.
Signed-off-by: Kevin Traynor
---
lib/dpif-netdev.c
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Add two counters to dp_netdev_rxq which will be used for storing the
processing cycles of an rxq. Processing cycles will be stored in reference
to a defined interval. One counter is used for storing cycles during the
current in progress interval, while
On 08/09/2017 08:45 AM, Kevin Traynor wrote:
Soon we will want to store processing cycle counts in the dp_netdev_rxq,
so use that as a basis for the polled_queue that pmd_thread_main uses.
Signed-off-by: Kevin Traynor
---
lib/dpif-netdev.c | 10 +-
1 file changed, 5 insertions(+), 5
Hi,
I understand your inbox is a busy place and sometimes it's natural to miss
few emails. I quickly wanted to check whether you had a chance to review my
email which I sent you.
Please let me know how you wish to proceed with this.
Thank you and look forward to hearing from you.
On 10 August 2017 at 11:41, Ben Pfaff wrote:
> On Thu, Aug 10, 2017 at 01:01:32PM +0800, Gao Zhenyu wrote:
>> How about:
>> struct ovsdb_idl_table {
>> ...
>> const struct ovsdb_idl_table_class *table_class
>>
>> }
>>
>> struct ovsdb_idl {
>>
>> const struct ovsdb_idl_class *idl
On Thu, Aug 10, 2017 at 4:43 PM, Ben Pfaff wrote:
> On Thu, Aug 10, 2017 at 04:20:23PM -0400, Russell Bryant wrote:
>> ovs-sandbox comes with a script to quickly set up a simple
>> OVN configuration, ovn-setup.sh. This script set up config in the OVN
>> northbound database, but didn't create the
On Thu, Aug 10, 2017 at 04:41:19PM -0400, Lance Richardson wrote:
> Some recent travis builds have failed due to having exceeded the
> per-job time limit of 50 minutes. This change enables parallel
> builds and parallel test execution in order to reduce overall
> execution time, and will hopefully
On Thu, Aug 10, 2017 at 03:33:55PM -0400, Aaron Conole wrote:
> Ben Pfaff writes:
>
> > On Wed, Aug 09, 2017 at 04:00:53PM -0400, Aaron Conole wrote:
> >> As part of a devargs rework in DPDK, the PCI header file was removed, and
> >> needs to be directly included. This isn't required to build wi
On Thu, Aug 10, 2017 at 04:20:23PM -0400, Russell Bryant wrote:
> ovs-sandbox comes with a script to quickly set up a simple
> OVN configuration, ovn-setup.sh. This script set up config in the OVN
> northbound database, but didn't create the corresponding ports on
> br-int. Add that to save anoth
On Thu, Aug 10, 2017 at 01:22:16PM -0700, Darrell Ball wrote:
> Reset the DPDK hwol flags in dp_packet_init_. The new hwol bad checksum
> flag is uninitialized for non-dpdk ports and this is noticed as test
> failures using netdev-dummy ports, when built with the --with-dpdk
> flag set. Hence, in
Some recent travis builds have failed due to having exceeded the
per-job time limit of 50 minutes. This change enables parallel
builds and parallel test execution in order to reduce overall
execution time, and will hopefully allow this class of build
failures to be avoided.
Since the travis build
On Wed, Aug 09, 2017 at 03:27:42PM -0700, Joe Stringer wrote:
> Now that the 'new' datum is named 'new_datum', be more consistent by
> renaming 'old' to 'old_datum' to match.
>
> Signed-off-by: Joe Stringer
> ---
> v2: New patch.
Oh, it's an additional patch. OK ;-)
Acked-by: Ben Pfaff
__
On Wed, Aug 09, 2017 at 03:27:41PM -0700, Joe Stringer wrote:
> In C++, 'new' is a keyword. If this is used as the name for a field,
> then C++ compilers can get confused about the context and fail to
> compile references to such fields. Rename the field to 'new_datum' to
> avoid this issue.
>
> S
On Thu, Aug 10, 2017 at 06:53:18PM +, Mark Michelson wrote:
> On Thu, Aug 10, 2017 at 1:14 PM Ben Pfaff wrote:
>
> > On Thu, Aug 10, 2017 at 02:41:30PM +, Mark Michelson wrote:
> > > I'm curious about the current behavior when ovn-controller originates a
> > > packet and transmits it over
Reset the DPDK hwol flags in dp_packet_init_. The new hwol bad checksum
flag is uninitialized for non-dpdk ports and this is noticed as test
failures using netdev-dummy ports, when built with the --with-dpdk
flag set. Hence, in this case, packets may be falsely marked as having a
bad checksum. The
ovs-sandbox comes with a script to quickly set up a simple
OVN configuration, ovn-setup.sh. This script set up config in the OVN
northbound database, but didn't create the corresponding ports on
br-int. Add that to save another step in provisioning this simple
environment.
Add "ovn-sbctl show" o
Darrell Ball writes:
> -Original Message-
> From: Aaron Conole
> Date: Thursday, August 10, 2017 at 10:13 AM
> To: Darrell Ball
> Cc: ovs dev
> Subject: Re: [ovs-dev] [patch_v4] dp-packet: Reset DPDK HWOL checksum flags
> on init.
>
> Darrell Ball writes:
>
> > -Orig
Ben Pfaff writes:
> On Wed, Aug 09, 2017 at 04:00:53PM -0400, Aaron Conole wrote:
>> As part of a devargs rework in DPDK, the PCI header file was removed, and
>> needs to be directly included. This isn't required to build with 17.05 or
>> earlier, but will be required should a future update happ
On Fri, Aug 04, 2017 at 10:31:14AM +0800, wang.qia...@zte.com.cn wrote:
> The function of consider_port_binding is redundant. This patch split the
> function to some sub-function by the port type.
>
> Signed-off-by: wang qianyu
Can you explain how it is redundant, and how this patch reduces it?
On Thu, Aug 10, 2017 at 1:14 PM Ben Pfaff wrote:
> On Thu, Aug 10, 2017 at 02:41:30PM +, Mark Michelson wrote:
> > I'm curious about the current behavior when ovn-controller originates a
> > packet and transmits it over a link-local IPv6 multicast address. Will
> the
> > packet be delivered o
>>
} else {
+/* If the queue is disabled in the guest, the
corresponding qid
+ * map shall be set to OVS_VHOST_QUEUE_DISABLED(-2).
+ *
+ * The packets that were queued in 'qid' could be
I like that.
On Thu, Aug 10, 2017 at 11:54:11AM +0800, Gao Zhenyu wrote:
> How about mutable --> is_mutable ?
>
>
> Thanks
> Zhenyu Gao
>
> 2017-08-10 6:27 GMT+08:00 Joe Stringer :
>
> > In C++, 'mutable' is a keyword. If this is used as the name for a field,
> > then C++ compilers can get con
On Thu, Aug 10, 2017 at 01:01:32PM +0800, Gao Zhenyu wrote:
> How about:
> struct ovsdb_idl_table {
> ...
> const struct ovsdb_idl_table_class *table_class
>
> }
>
> struct ovsdb_idl {
>
> const struct ovsdb_idl_class *idl_class;
>
Why make it longer?
> Besides of that, I
On Wed, Aug 09, 2017 at 04:00:53PM -0400, Aaron Conole wrote:
> As part of a devargs rework in DPDK, the PCI header file was removed, and
> needs to be directly included. This isn't required to build with 17.05 or
> earlier, but will be required should a future update happen.
>
> Signed-off-by: A
OK.
I see what you're talking about. It's not a bug, then. OVSDB is just
doing its job ensuring referential integrity.
Please feel free to submit a patch to implement the feature that you
want.
On Thu, Aug 10, 2017 at 06:07:09AM +0530, Arunkumar Rg wrote:
> Hi Ben,
>
> Thanks for your respons
On Wed, Aug 9, 2017 at 4:36 PM, Aaron Conole wrote:
> This commit builds on the non-root ovs work and adds a udev rule which will
> automatically set the group permissions of vfio devices.
>
> Signed-off-by: Aaron Conole
> ---
> Systemd folks say that this is not something that should be a part o
I'm inclined to make the action name specific to the header,
e.g. encap_nsh, decap_nsh. There doesn't have to be a one-to-one
correspondence between syntax and OpenFlow encoding.
On Thu, Aug 10, 2017 at 03:25:20PM +, Jan Scheurich wrote:
> The generic code today in function parse_ENCAP() uses
On Thu, Aug 10, 2017 at 02:41:30PM +, Mark Michelson wrote:
> I'm curious about the current behavior when ovn-controller originates a
> packet and transmits it over a link-local IPv6 multicast address. Will the
> packet be delivered only to nodes on the same chassis, or can the packet
> also re
-Original Message-
From: Aaron Conole
Date: Thursday, August 10, 2017 at 10:13 AM
To: Darrell Ball
Cc: ovs dev
Subject: Re: [ovs-dev] [patch_v4] dp-packet: Reset DPDK HWOL checksum flags on
init.
Darrell Ball writes:
> -Original Message-
> From: Aaron Conole
Darrell Ball writes:
> -Original Message-
> From: Aaron Conole
> Date: Wednesday, August 9, 2017 at 12:51 PM
> To: Darrell Ball
> Cc: Joe Stringer , Darrell Ball , ovs
> dev
> Subject: Re: [ovs-dev] [patch_v4] dp-packet: Reset DPDK HWOL checksum flags
> on init.
>
> Darrell Ball
9th August 2017
ATTENDEES: Aaron C, Antonio F, Ciara L, Darrell B,
Olga A, Sugesh C, Mark K, Michael L, Johan T, Peter S, Ian S, Kevin T,
Yipeng W, Billy O'M, Finn C, Georg S, Jan S, Simon H, Ben P, Ori, (may
have missed some)
===
GENERAL
===
- OVS 2.8
-- OVS 2.8 branched
-- Looking at en
On 08/08/2017 11:23 AM, Joe Stringer wrote:
An upcoming patch will reuse this from elsewhere.
Signed-off-by: Joe Stringer
---
lib/netdev.c | 14 ++
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/lib/netdev.c b/lib/netdev.c
index 7e9896b82928..3e8b211857d7 100644
-
Conditional EMC insert helps a lot in scenarios with high numbers
of parallel flows, but in current implementation this option affects
all the threads and ports at once. There are scenarios there we have
different number of flows on different ports. For example, if one
of the VMs encapsulates traff
In current implementation 'now' variable updated once on each
receive cycle and passed through the whole datapath via function
arguments. It'll be better to keep this variable inside PMD
thread structure to be able to get it at any time. Such solution
will save the stack memory and simplify possibl
Ilya Maximets (2):
dpif-netdev: Keep latest measured time for PMD thread.
dpif-netdev: Per-port conditional EMC insert.
Documentation/howto/dpdk.rst | 4 +-
NEWS | 2 +-
lib/dpif-netdev.c| 223 ++-
tests/pmd.at
-Original Message-
From: Darrell Ball
Date: Wednesday, August 9, 2017 at 1:38 PM
To: "Chandran, Sugesh" , Ben Pfaff
Cc: "d...@openvswitch.org"
Subject: Re: [ovs-dev] [patch_v5] dp-packet: Reset DPDK HWOL checksum flags on
init.
-Original Message-
From: "Chan
This allows to collect packets from more than one RX burst
and send them together with a configurable maximum latency.
'other_config:output-max-latency' can be used to configure
time that a packet can wait in output batch for sending.
Signed-off-by: Ilya Maximets
---
Notes:
* This is an RFC
Cutlen already applied while processing OVS_ACTION_ATTR_OUTPUT.
Signed-off-by: Ilya Maximets
---
lib/netdev-dpdk.c | 5 -
1 file changed, 5 deletions(-)
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 8e3158f..ddcc574 100644
--- a/lib/netdev-dpdk.c
+++ b/lib/netdev-dpdk.c
@@ -1819,
Not needed anymore because 'may_steal' already handled on
dpif-netdev layer and always true;
Signed-off-by: Ilya Maximets
---
lib/dpif-netdev.c | 2 +-
lib/netdev-bsd.c | 4 ++--
lib/netdev-dpdk.c | 25 +++--
lib/netdev-dummy.c| 4 ++--
lib/netdev-linux.c
While processing incoming batch of packets they are scattered
across many per-flow batches and sent separately.
This becomes an issue while using more than a few flows.
For example if we have balanced-tcp OvS bonding with 2 ports
there will be 256 datapath internal flows for each dp_hash
pattern.
This patch-set inspired by [1] from Bhanuprakash Bodireddy.
Implementation of [1] looks very complex and introduces many pitfalls [2]
for later code modifications like possible packet stucks.
This version targeted to make simple and flexible output packet batching on
higher level without introduci
The generic code today in function parse_ENCAP() uses the encap header string
also as string for the property class. I am afraid that implementer of
subsequent encap headers might not realize that this is a temporary
implementation shortcut that should have been generalized.
The minimum we shou
[ View in browser ]( http://r.newsletter.bonescamail.nl/nru6rn1aoatrf.html
)
[ ]( http://r.newsletter.bonescamail.nl/click/2n3cr2k4taoatrd.html )
[ Click here for our complete pricelist! ](
http://r.newsletter.bonescamail.nl/click/2n3cr2k5lqoatrd.html )
SPECIAL PROM
Hi,
I'm curious about the current behavior when ovn-controller originates a
packet and transmits it over a link-local IPv6 multicast address. Will the
packet be delivered only to nodes on the same chassis, or can the packet
also reach on-link nodes on other chassis?
The reason I ask is that I'm w
>
> On 08/09/2017 10:00 PM, Aaron Conole wrote:
> > As part of a devargs rework in DPDK, the PCI header file was removed, and
> > needs to be directly included. This isn't required to build with 17.05 or
> > earlier, but will be required should a future update happen.
> >
> > Signed-off-by: Aaron
On 08/09/2017 10:00 PM, Aaron Conole wrote:
> As part of a devargs rework in DPDK, the PCI header file was removed, and
> needs to be directly included. This isn't required to build with 17.05 or
> earlier, but will be required should a future update happen.
>
> Signed-off-by: Aaron Conole
Trie
OVS master and 2.8 branch has merged NSH userspace
patch series, this patch is to enable NSH support
in kernel data path in order that OVS can support
NSH in 2.8 release in compat mode by porting this.
Signed-off-by: Yi Yang
---
drivers/net/vxlan.c | 7 ++
include/net/nsh.h
58 matches
Mail list logo