Hi,
so after the discussion it turned out that summarized info about pmd threads
will be enough. I'm going to prepare the patch where those new sflow counters
will look as follows:
struct dpif_pmd_stats {
unsigned num_threads; /* Number of PMD threads */
uint64_t cycles_polling;
From caeb84217c38ccd0b2076689fd36b578c00678ad Mon Sep 17 00:00:00 2001
From: xubinbin
Date: Thu, 21 Jul 2016 21:52:29 +0800
Subject: [PATCH] netdev-dpdk: remove duplicated code in
netdev_dpdk_get_status
Put "driver_name" into "args" twice, that's meaninglessness.
So need to remove duplicated cod
ovs.db.idl.Datum.from_python fails to handle set type value, while set
type is also a common iterable sequence, just like list and tuple.
No reason IDL caller must to turn set type parameters to list or tuple
type. Otherwise, they will fail to insert data, but get no exception.
Signed-off-by: Zong
On Wed, Jul 20, 2016 at 02:55:19PM -0700, Ben Pfaff wrote:
> Found by inspection.
>
> Signed-off-by: Ben Pfaff
I found another one, in patch.c, so I sent a v2:
http://openvswitch.org/pipermail/dev/2016-July/075785.html
___
dev mailing list
dev@
Found by inspection.
Signed-off-by: Ben Pfaff
---
v1->v2: Found another one to fix.
ovn/controller/encaps.c | 11 ---
ovn/controller/patch.c | 2 +-
2 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/ovn/controller/encaps.c b/ovn/controller/encaps.c
index 03ec732..977cc3a
OVN implements a native DHCPv4 support which caters to the common
use case of providing an IP address to a booting instance by
providing stateless replies to DHCPv4 requests based on statically
configured address mappings. To do this it allows a short list of
DHCPv4 options to be configured and app
- This mail is in HTML. Some elements may be ommited in plain text. -
Good Day ,
Attached is the payment acknowledgement from our valued customer to you.
Will Burton
Accountant
Orient Exchange Co. (L.L.C.)
Mohd. & Obaid Al Mulla Building, Shop No. 4,
Street No 18, Community 119
Next To Twin Tower
It's clear enough, thanks a lot, Jan
But http://openvswitch.org/pipermail/dev/2016-May/071657.html also mentioned
recirculate will result in 35% performance degradation, for SFC use case, this
is really a serious issue, how do you think we can alleviate this very
efficiently?
I think the perfo
The ovsdb replication feature is not specific to the ovsdb socket types.
Switching the tests to use Unix domain socket simplifies the tests.
Signed-off-by: Andy Zhou
Although they don't make any difference in my local testing, travis
tests are less likely to report intermittent replication t
> On Jul 20, 2016, at 2:26 PM, Russell Bryant wrote:
>
> After some help rebasing and re-testing from Babu Shanmugam, I went through
> this again, addressed comments, and applied this to master.
Great! Glad to see it finally merged. Thanks for being patient with me.
--Justin
_
> On Jul 20, 2016, at 7:25 AM, Hui Kang wrote:
>
> "dev" wrote on 07/19/2016 04:15:56 PM:
>
> > From: Justin Pettit
> > To: Hui Kang
> > Cc: dev@openvswitch.org
> > Date: 07/19/2016 04:16 PM
> > Subject: Re: [ovs-dev] [PATCH v3] [OVN-northd] Rename nbs/nbr port
> > names to nbsp/nbrp
> > Se
I thought you were just surprised to see one of your patches reviewed quickly.
--Justin
> On Jul 20, 2016, at 4:09 PM, Ben Pfaff wrote:
>
> This isn't the kind of review I'm used to. Are you impersonating Mork
> with a speech impediment, or is there more to it?
>
> On Wed, Jul 20, 2016 at 04
This isn't the kind of review I'm used to. Are you impersonating Mork
with a speech impediment, or is there more to it?
On Wed, Jul 20, 2016 at 04:05:18PM -0700, Justin Pettit wrote:
> NACK! NACK! NACK!
>
> > On Jul 20, 2016, at 4:04 PM, Ben Pfaff wrote:
> >
> > Signed-off-by: Ben Pfaff
> > -
NACK! NACK! NACK!
> On Jul 20, 2016, at 4:04 PM, Ben Pfaff wrote:
>
> Signed-off-by: Ben Pfaff
> ---
> FAQ.md | 7 +++
> 1 file changed, 7 insertions(+)
>
> diff --git a/FAQ.md b/FAQ.md
> index 063bd70..7f72b5c 100644
> --- a/FAQ.md
> +++ b/FAQ.md
> @@ -118,6 +118,13 @@ A: Starting in OVS
Signed-off-by: Ben Pfaff
---
FAQ.md | 7 +++
1 file changed, 7 insertions(+)
diff --git a/FAQ.md b/FAQ.md
index 063bd70..7f72b5c 100644
--- a/FAQ.md
+++ b/FAQ.md
@@ -118,6 +118,13 @@ A: Starting in OVS 2.4, we switched the default ports to
the
cannot, all the programs allow overriding t
Found by inspection.
Signed-off-by: Ben Pfaff
---
ovn/controller/encaps.c | 11 ---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/ovn/controller/encaps.c b/ovn/controller/encaps.c
index 03ec732..977cc3a 100644
--- a/ovn/controller/encaps.c
+++ b/ovn/controller/encaps.c
@@
On Thu, Jul 7, 2016 at 1:13 PM, Justin Pettit wrote:
>
> > On Jun 30, 2016, at 10:14 PM, Russell Bryant wrote:
> >
> > diff --git a/ovn/northd/ovn-northd.8.xml b/ovn/northd/ovn-northd.8.xml
> > index 260cc14..d2bddcb 100644
> > --- a/ovn/northd/ovn-northd.8.xml
> > +++ b/ovn/northd/ovn-northd.8.
This commit builds upon some of the recent ovs-ctl changes to build a
more integrated systemd setup. A new service (ovs-vswitchd) is
added to track the ovs-vswitchd, and ovsdb-server service is reserved
for the ovsdb-server daemon. The systemd scripts still use ovs-ctl to
actually initialize the
These patches make adjustments to the way systemd is done so that we have:
* one daemon started per service
* services which correspond to actual daemon names
* a single 'dummy' service to start all at once
* some convenient information to poll from systemd.
These have been tested on Fedora 23 an
This commit allows the ovs-ctl command to spawn daemons without the
internal process monitor. This is useful when integrating with,
ex. systemd, which provides its own monitoring facilities.
Signed-off-by: Aaron Conole
Acked-by: Ben Pfaff
Acked-by: Flavio Leitner
---
utilities/ovs-ctl.8 | 5
Currently, openvswitch.service calls out to start
openvswitch-nonetwork.service. However, openvswitch-nonetwork.service
will be called ovsdb-server, so that it is a bit more reflective of
the dependencies. This commit does make the file a bit of a misnomer as
currently the ovsdb-server SERVICE wi
vxlan driver has bypass for local vxlan traffic, but that
depends on information about all VNIs on local system in
vxlan driver. This is not available in case of LWT.
Therefore following patch disable encap bypass for LWT
vxlan traffic.
Reported-by: Jakub Libosvar
Signed-off-by: Pravin B Shelar
On Mon, Jul 18, 2016 at 11:22 AM, Ryan Moats wrote:
> "dev" wrote on 07/18/2016 07:50:06 AM:
>
> > From: Chandra Sekhar Vejendla/San Jose/IBM@IBMUS
> > To: dev@openvswitch.org
> > Date: 07/18/2016 07:50 AM
> > Subject: [ovs-dev] [PATCH] ovn: Add datapth of gateway port to
> local_datapaths
> > S
On Wed, Jul 20, 2016 at 03:48:08PM -0400, Russell Bryant wrote:
> On Wed, Jul 20, 2016 at 12:30 PM, Ben Pfaff wrote:
>
> > On Wed, Jul 20, 2016 at 10:00:22AM -0400, Russell Bryant wrote:
> > > On Tue, Jul 19, 2016 at 1:58 PM, Ben Pfaff wrote:
> > >
> > > > This document has two different kinds o
On Wed, Jul 20, 2016 at 12:30 PM, Ben Pfaff wrote:
> On Wed, Jul 20, 2016 at 10:00:22AM -0400, Russell Bryant wrote:
> > On Tue, Jul 19, 2016 at 1:58 PM, Ben Pfaff wrote:
> >
> > > This document has two different kinds of text:
> > >
> > >- The first sections of the document, "Release Strate
Source: openvswitch
Version: 2.5.1~pre+git20160626-2
Severity: important
Tags: stretch sid
User: debian...@lists.debian.org
Usertags: qa-ftbfs-20160720 qa-ftbfs qa-indep
Justification: FTBFS on amd64
Hi,
During a rebuild of all packages in sid, your package failed to build on
amd64. This
Reply to: cop...@openvswitch.com
Device Name: cop...@openvswitch.com
Device Model: MX-2310U
File Format: Microsoft Office Word
Resolution: 200dpi x 200dpi
Attached file is scanned image in Microsoft Office Word format.
Use Microsoft Office Word to view the document.
_
Sorry for the late reply. I missed this sub-thread somehow.
On Thu, Jul 14, 2016 at 09:38:09AM +0800, Xiao Liang wrote:
> As far as I know, Eric and Tom are working on the kernel patch set and
> would submit a new version to net-next. Kernel patches usually go to
> netdev first and then backported
>
> On Wed, Jul 20, 2016 at 6:43 PM, Gray, Mark D
> wrote:
> > [Gray, Mark D] I think we should focus on one or two use cases rather
> > than a general offload like you discuss below. A general offload
> > involves a huge amount of code churn and there are a lot of difficulties,
> some that you
On Tue, Jul 19, 2016 at 5:02 PM, Simon Horman
wrote:
> On Mon, Jul 18, 2016 at 03:34:52PM -0700, pravin shelar wrote:
>> On Sun, Jul 17, 2016 at 9:50 PM, Simon Horman
>> wrote:
>> > [CC Jiri Benc for portion regarding GRE]
>> >
>> > Hi Pravin,
>> >
>> > On Fri, Jul 15, 2016 at 02:07:37PM -0700, p
On Wed, Jul 20, 2016 at 6:43 PM, Gray, Mark D wrote:
> [Gray, Mark D] I think we should focus on one or two use cases rather than
> a general offload like you discuss below. A general offload involves a huge
> amount of code
> churn and there are a lot of difficulties, some that you have highlig
On Wed, Jul 20, 2016 at 5:06 PM, Paul Quinn (paulq) wrote:
>
>> On Jul 14, 2016, at 11:39 AM, Jesse Gross wrote:
>>
>> On Wed, Jul 13, 2016 at 10:44 PM, Elzur, Uri wrote:
>>> +1 on starting w MD Type = 1
>>>
>>> Not sure I understand the concern expressed with " implementations that
>>> don't i
> Hi Dev Team,
>
> I submitted a RFC patch few months ago to optimize the tunneling
> performance in OVS-DPDK (specifically VxLAN performance) using Intel
> Fortville Flow director feature. More details about the patch can be found
> below.
>
> http://openvswitch.org/pipermail/dev/2016-March/0679
On Wed, Jul 20, 2016 at 10:00:22AM -0400, Russell Bryant wrote:
> On Tue, Jul 19, 2016 at 1:58 PM, Ben Pfaff wrote:
>
> > This document has two different kinds of text:
> >
> >- The first sections of the document, "Release Strategy" and "Release
> > Numbering", describe what we've alread
At the end of my initial long response
(http://openvswitch.org/pipermail/dev/2016-July/075115.html) I had included an
example for how the OF pipeline could be programmed if the NSH fields are
treated as packet header match fields and not metadata fields. As you say, the
interesting case is how
This commit extends the chutil library by providing a set of helpers
which operate on files already opened by the process.
The implementation provided only works with linux systems, but any
system which provides a system call mechanism to do this (such as
FreeBSD), could be used. The linux implem
It will be useful in the future to be able to set ownership and permissions
on files which Open vSwitch creates. Allowing the specification of such
ownership and permissions using the standard user:group, uog+-rwxs, and
numerical forms commonly associated with those actions.
This patch introduces
Currently, when using Open vSwitch with DPDK and qemu guests, the recommended
method for joining the guests is via the dpdkvhostuser interface. This
interface uses Unix Domain sockets to communicate. When these sockets are
created, they inherit the permissions and ownership from the vswitchd proces
Aaron Conole writes:
> Currently, when using Open vSwitch with DPDK and qemu guests, the recommended
> method for joining the guests is via the dpdkvhostuser interface. This
> interface uses Unix Domain sockets to communicate. When these sockets are
> created, they inherit the permissions and own
The message could not be delivered
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
Currently, when dpdkvhostuser devices are created, they inherit whatever the
running umask and uid/gid of the vswitchd process. This leads to difficulties
when using vhost_user consumers (such as qemu).
This patch introduces two new database entries, 'vhost-sock-owner' to set the
ownership, and 'v
Hi Yi,
Recirculation is implicitly triggered by calling ctx_trigger_freeze(ctx) at
the end of the composition phase of an action.
The example for this is pop_mpls, but unfortunately it is a bit hidden there
because the invocation of ctx_trigger_freeze(ctx) is deferred in order to
avoid unne
> On Jul 14, 2016, at 11:39 AM, Jesse Gross wrote:
>
> On Wed, Jul 13, 2016 at 10:44 PM, Elzur, Uri wrote:
>> +1 on starting w MD Type = 1
>>
>> Not sure I understand the concern expressed with " implementations that
>> don't implement TLVs will become deployed and then when there is a use f
ovn-northd processes the list of Port_Bindings and hashes the list of
queues per chassis. When it finds a port with qos_parameters and without
a queue_id, it allocates a free queue for the chassis that this port belongs.
The queue_id information is stored in the options field of Port_binding table.
ovn-northd sets 'ip.dscp' to the DSCP value
Signed-off-by: Babu Shanmugam
Acked-by: Ben Pfaff
---
ovn/controller/lflow.c | 2 +-
ovn/northd/ovn-northd.c | 4
ovn/ovn-nb.xml | 6 ++
ovn/ovn-sb.xml | 5 +
4 files changed, 16 insertions(+), 1 deletion(-)
diff --git
From: Babu Shanmugam
v5->v6:
- Rebased to the latest master
- Avoid updating the qos column of port record when txn is NULL
Babu Shanmugam (2):
Check and allocate free qdisc queue id for ports with qos parameters
DSCP marking on packets egressing VIF interface
ovn/controller/bindin
"dev" wrote on 07/19/2016 04:15:56 PM:
> From: Justin Pettit
> To: Hui Kang
> Cc: dev@openvswitch.org
> Date: 07/19/2016 04:16 PM
> Subject: Re: [ovs-dev] [PATCH v3] [OVN-northd] Rename nbs/nbr port
> names to nbsp/nbrp
> Sent by: "dev"
>
>
> > On Jul 19, 2016, at 11:36 AM, Hui Kang wrote:
On Tue, Jul 19, 2016 at 1:58 PM, Ben Pfaff wrote:
> This document has two different kinds of text:
>
>- The first sections of the document, "Release Strategy" and "Release
> Numbering", describe what we've already been doing for most of the
> history of Open vSwitch. If there is an
Hi sorry for the delay
Replies inline.
> -Original Message-
> From: Aaron Conole [mailto:acon...@redhat.com]
> Sent: Monday, July 11, 2016 6:44 PM
> To: Mooney, Sean K
> Cc: Flavio Leitner ; dev@openvswitch.org
> Subject: Re: [ovs-dev] [PATCH v2] ovsdb: Expose vhost-user socket directory
Reply to: cop...@openvswitch.com
Device Name: cop...@openvswitch.com
Device Model: MX-2310U
File Format: Microsoft Office Word
Resolution: 200dpi x 200dpi
Attached file is scanned image in Microsoft Office Word format.
Use Microsoft Office Word to view the document.
_
This message was not delivered due to the following reason:
Your message was not delivered because the destination server was
not reachable within the allowed queue period. The amount of time
a message is queued before it is returned depends on local configura-
tion parameters.
Most likely there
Reply to: cop...@openvswitch.com
Device Name: cop...@openvswitch.com
Device Model: MX-2310U
File Format: Microsoft Office Word
Resolution: 200dpi x 200dpi
Attached file is scanned image in Microsoft Office Word format.
Use Microsoft Office Word to view the document.
_
Hi Ryan,
Thank you for your advice. The controller will drop the icmp4 packet whose
eth.src or eth.dst is
broadcast/multicast address and the type of icmp4 is “destination unreachable”.
That may reduce
the broadcast storm attack(e.g. icmp flood, dhcp flood). I write the rate
limiting of icmp4 i
On Wed, Jul 20, 2016 at 4:50 AM, Justin Pettit wrote:
>
>> On Jul 13, 2016, at 3:19 AM, Zong Kai Li wrote:
>>
>> Hi, Justin. I tried your patches one by one. P1~P5 are OK.
>> But something wrong seems happened to P6.
>> In my OpenStack integrated environment, after using P6, I cannot ping
>> VM d
54 matches
Mail list logo