On 03/04/2015 10:42 PM, David Miller wrote:
From: Tom Herbert
Date: Wed, 4 Mar 2015 21:20:41 -0800
On Wed, Mar 4, 2015 at 9:00 PM, David Miller wrote:
From: John Fastabend
Date: Wed, 04 Mar 2015 17:54:54 -0800
I think a set operation _is_ necessary for OVS and other
applications that run
On Wed, Mar 04, 2015 at 10:49:39PM -0800, Justin Pettit wrote:
> On Mar 4, 2015, at 10:36 PM, Ben Pfaff wrote:
> >
> > Some of the comment wording is odd, e.g. on
> > ovsrec_autoattach_set_mappings():
> >
> > * The value must be key in range 0 to 16,777,215, value in range 0 to 4,095.
> >
> > o
On Mar 4, 2015, at 10:36 PM, Ben Pfaff wrote:
>
> Some of the comment wording is odd, e.g. on
> ovsrec_autoattach_set_mappings():
>
> * The value must be key in range 0 to 16,777,215, value in range 0 to 4,095.
>
> or on ovsrec_bridge_set_flow_tables():
>
> * The value must be key in range 0 t
From: Tom Herbert
Date: Wed, 4 Mar 2015 21:20:41 -0800
> On Wed, Mar 4, 2015 at 9:00 PM, David Miller wrote:
>> From: John Fastabend
>> Date: Wed, 04 Mar 2015 17:54:54 -0800
>>
>>> I think a set operation _is_ necessary for OVS and other
>>> applications that run in user space.
>>
>> It's neces
On Wed, Mar 04, 2015 at 10:29:36PM -0800, Justin Pettit wrote:
>
> > On Mar 4, 2015, at 10:00 PM, Ben Pfaff wrote:
> >
> > On Wed, Mar 04, 2015 at 06:09:17PM -0800, Justin Pettit wrote:
> >> Signed-off-by: Justin Pettit
> >> ---
> >> v1->v2: - Add more comments based on suggestions from Ben.
>
> On Mar 4, 2015, at 10:00 PM, Ben Pfaff wrote:
>
> On Wed, Mar 04, 2015 at 06:09:17PM -0800, Justin Pettit wrote:
>> Signed-off-by: Justin Pettit
>> ---
>> v1->v2: - Add more comments based on suggestions from Ben.
>>- Fix whitespace issue.
>
> Doesn't appear to apply to current maste
On Wed, Mar 04, 2015 at 06:09:17PM -0800, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
> ---
> v1->v2: - Add more comments based on suggestions from Ben.
> - Fix whitespace issue.
Doesn't appear to apply to current master or ovn branches, but you
didn't repost the whole series. I
On Wed, Mar 04, 2015 at 10:21:49PM -0500, Russell Bryant wrote:
> Update the TODO list for the Neutron plugin to reflect the repository
> that was created for it, as well as the plugin specific TODO list that
> lives in that repo.
>
> Signed-off-by: Russell Bryant
Thanks! I applied this. I ref
On Wed, Mar 4, 2015 at 9:00 PM, David Miller wrote:
> From: John Fastabend
> Date: Wed, 04 Mar 2015 17:54:54 -0800
>
>> I think a set operation _is_ necessary for OVS and other
>> applications that run in user space.
>
> It's necessary for the kernel to internally manage the chip
> flow resources
From: John Fastabend
Date: Wed, 04 Mar 2015 17:54:54 -0800
> I think a set operation _is_ necessary for OVS and other
> applications that run in user space.
It's necessary for the kernel to internally manage the chip
flow resources.
Full stop.
It's not being exported to userspace. That is exa
No matter how busy you are, dont deprive yourself of sex!
http://urla.ru/1HAS
&
http://urla.ru/1HBd2
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
Update the TODO list for the Neutron plugin to reflect the repository
that was created for it, as well as the plugin specific TODO list that
lives in that repo.
Signed-off-by: Russell Bryant
---
ovn/TODO | 14 --
1 file changed, 4 insertions(+), 10 deletions(-)
diff --git a/ovn/TODO
These changes all look good to me, I really like the unit32_t-as-a-stack
idea.
---Peter
On Tue, 03 Mar 2015 21:41:11 -0800: Ben Pfaff wrote:
On Mon, Feb 23, 2015 at 08:48:59AM -0800, Alex Wang wrote:
>> From: Peter Amidon
>>
>> This patch adds bash command-line completion script fo
On Wed, Mar 4, 2015 at 2:13 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 11:35:00AM -0800, Justin Pettit wrote:
> > A chassis may support multiple encapsulation types, so break them out
> > into their own table.
> >
> > Signed-off-by: Justin Pettit
>
> Thank you for the patches!
>
> "git am" s
Signed-off-by: Justin Pettit
---
v1->v2: - Add more comments based on suggestions from Ben.
- Fix whitespace issue.
---
ovsdb/ovsdb-idlc.in | 92 +-
1 files changed, 75 insertions(+), 17 deletions(-)
diff --git a/ovsdb/ovsdb-idlc.in b/ovs
On Wed, Mar 4, 2015 at 1:40 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 11:25:51AM -0800, Justin Pettit wrote:
> > Signed-off-by: Justin Pettit
>
> "git" says:
>
> Applying: ovsdb-idlc: Generate comments for "*_set" functions.
> /home/blp/ovs/.git/rebase-apply/patch:81: trailing white
[...]
Doesn't this imply two entities to be independently managing the same
physical resource? If so, this raises questions of how the resource
would be partitioned between them? How are conflicting requests
between the two rectified?
What two entities? The driver + flow API code I have in th
On Wed, Mar 04, 2015 at 05:28:48PM -0800, Ben Pfaff wrote:
> On Wed, Feb 18, 2015 at 09:01:31AM -0500, Simon Horman wrote:
> > On Tue, Feb 17, 2015 at 11:43:21AM -0800, Ben Pfaff wrote:
> > > On Sun, Feb 15, 2015 at 02:13:14PM -0500, Simon Horman wrote:
> > > > On Sun, Feb 15, 2015 at 08:51:31AM -0
On 03/04/2015 04:04 PM, David Christensen wrote:
That said, my working assumptions are:
* That Open vSwitch may manage flow offloads from user-space. This is as
opposed to them being transparently handled in the datapath. This does
not preclude the existence of transparent offloading in th
On Wed, Mar 04, 2015 at 03:21:42PM -0800, Ben Pfaff wrote:
> On Thu, Mar 05, 2015 at 12:06:14AM +0100, Raul Suarez Marin wrote:
> > Thank you for your fast response. I configured my ovs with --enable-Werror
> > and this allowed me to fix a couple warnings (unused variables). Sadly,
> > looks like a
Signed-off-by: Ben Pfaff
---
FAQ.md | 19 ++-
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/FAQ.md b/FAQ.md
index 5ee529c..70dfd9c 100644
--- a/FAQ.md
+++ b/FAQ.md
@@ -1705,11 +1705,20 @@ A: Add your new message to "enum ofpraw" and "enum
ofptype" in
A: Add
On Wed, Feb 18, 2015 at 09:01:31AM -0500, Simon Horman wrote:
> On Tue, Feb 17, 2015 at 11:43:21AM -0800, Ben Pfaff wrote:
> > On Sun, Feb 15, 2015 at 02:13:14PM -0500, Simon Horman wrote:
> > > On Sun, Feb 15, 2015 at 08:51:31AM -0800, Ben Pfaff wrote:
> > > > On Fri, Feb 13, 2015 at 06:14:28PM -0
Thanks for the extra info.
I have some more comments.
I think that the addition of 'rule_cookie' could easily be broken out
into a separate patch just before the main one. If you agree, would
you mind doing that? It took me a minute to verify that it was
essentially independent.
xlate_lookup_o
We're just waiting on support for the "conntrack" action in the
kernel. A few weeks to a month, I guess.
On Thu, Mar 05, 2015 at 05:50:09AM +0530, tech_kals Kals wrote:
> Hi Ben,
>
> Thanks a lot for your response. May I know when OVS 2.4 will be released ?
>
> On Wed, Mar 4, 2015 at 9:50 PM, B
Hi Ben,
Thanks a lot for your response. May I know when OVS 2.4 will be released ?
On Wed, Mar 4, 2015 at 9:50 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 05:18:55PM +0530, tech_kals Kals wrote:
> > am planning to use Broadcom OFDPA which will support multiple flow
> tables
> > in the hardw
Hey man...
Want to know a fast and easy way to get any woman
turned on, attracted to you, and on her knees, begging
to suck your d*ck?
This Video Shows You How http://link.ac/4Ned4
<--
Just click the link above to watch the video and insantly
discover..
-3 M
> > That said, my working assumptions are:
> >
> > * That Open vSwitch may manage flow offloads from user-space. This is as
> > opposed to them being transparently handled in the datapath. This does
> > not preclude the existence of transparent offloading in the datapath.
> > But rather limit
On Wed, Mar 4, 2015 at 1:48 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 11:25:53AM -0800, Justin Pettit wrote:
> > The warning is now captured in the C file, which has documentation for
> > all the public functions.
> >
> > Signed-off-by: Justin Pettit
>
> Acked-by: Ben Pfaff
>
Thanks. I'l
On Wed, Mar 4, 2015 at 1:48 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 11:25:52AM -0800, Justin Pettit wrote:
> > Signed-off-by: Justin Pettit
>
> This comment might be even better if it made it clearer how
> transactions work. Maybe "The caller must have started a transaction
> with ovsdb_
On Wed, Mar 04, 2015 at 03:32:03PM -0800, Justin Pettit wrote:
> On Wed, Mar 4, 2015 at 1:26 PM, Ben Pfaff wrote:
>
> > On Wed, Mar 04, 2015 at 11:25:50AM -0800, Justin Pettit wrote:
> > > Signed-off-by: Justin Pettit
> >
> > I agree that this is more user-friendly but it runs the risk that
> >
On Wed, Mar 4, 2015 at 1:26 PM, Ben Pfaff wrote:
> On Wed, Mar 04, 2015 at 11:25:50AM -0800, Justin Pettit wrote:
> > Signed-off-by: Justin Pettit
>
> I agree that this is more user-friendly but it runs the risk that
> someone will name an smap column "row" or "datum" or "auto" or
> "switch" or
On Thu, Mar 05, 2015 at 12:06:14AM +0100, Raul Suarez Marin wrote:
> Thank you for your fast response. I configured my ovs with --enable-Werror
> and this allowed me to fix a couple warnings (unused variables). Sadly,
> looks like all changes that I should have done, are already done.
>
> The chan
On Wed, Mar 4, 2015 at 1:59 PM, Andy Zhou wrote:
> It probably needs to fold in the following changes. Without them,
> there are compiler warnings.
>
> With those changes,
> Acked-by: Andy Zhou
>
>
> diff --git a/datapath/actions.c b/datapath/actions.c
> index 0d9..296ab79 100644
> --- a/data
Hello,
Thank you for your fast response. I configured my ovs with --enable-Werror
and this allowed me to fix a couple warnings (unused variables). Sadly,
looks like all changes that I should have done, are already done.
The changes that the FAQ proposes are related to OF messages and flow entry
i
Pushed to master,
Jarno
> On Mar 3, 2015, at 11:47 AM, Jarno Rajahalme wrote:
>
>
>> On Mar 3, 2015, at 10:00 AM, Ben Pfaff wrote:
>>
>> On Tue, Feb 24, 2015 at 03:42:02PM -0800, Jarno Rajahalme wrote:
>>> Signed-off-by: Jarno Rajahalme
>>
>> Does this fix a bug that someone noticed, or
> On Mar 3, 2015, at 10:22 AM, Ben Pfaff wrote:
>
> On Tue, Feb 24, 2015 at 03:42:05PM -0800, Jarno Rajahalme wrote:
>> There is no point trying to create ukeys for non-miss upcalls, such as
>> upcalls due to an explicit userspace actions.
>>
>> Signed-off-by: Jarno Rajahalme
>
> At first gla
Pushed to master,
Jarno
> On Mar 3, 2015, at 10:10 AM, Ben Pfaff wrote:
>
> On Tue, Feb 24, 2015 at 03:42:04PM -0800, Jarno Rajahalme wrote:
>> Signed-off-by: Jarno Rajahalme
>
> Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswitch.org
http:
Thanks for the review, pushed to master.
Jarno
> On Mar 3, 2015, at 9:58 AM, Ben Pfaff wrote:
>
> On Tue, Feb 24, 2015 at 03:42:00PM -0800, Jarno Rajahalme wrote:
>> Translate action set only if not dropping the packet.
>>
>> Signed-off-by: Jarno Rajahalme
>
> Acked-by: Ben Pfaff
___
On Wed, Mar 04, 2015 at 10:55:54PM +0100, Raul Suarez Marin wrote:
> I need new match options for my openvswitch. I have already sorted out the
> flow_mod message handling and everything. Now, I need to find where the
> match is performed, but I cannot find it.
>
> Anyone has a clue on where packe
On Wed, Mar 04, 2015 at 10:11:39AM -0800, Gurucharan Shetty wrote:
> On Fri, Jan 30, 2015 at 1:23 PM, Ben Pfaff wrote:
> > The manpage was poorly organized and failed to mention some options.
> > ---
> > utilities/bugtool/ovs-bugtool.8.in | 58
> > --
> > 1 fi
On Wed, Mar 04, 2015 at 11:35:00AM -0800, Justin Pettit wrote:
> A chassis may support multiple encapsulation types, so break them out
> into their own table.
>
> Signed-off-by: Justin Pettit
Thank you for the patches!
"git am" says:
Applying: ovn: Break encaps into separate table.
/ho
On Wed, Mar 04, 2015 at 11:34:59AM -0800, Justin Pettit wrote:
> Let two consenting transport nodes choose how they want to talk; we
> don't need to be so prescriptive in the supported encap types for OVN.
>
> Signed-off-by: Justin Pettit
I agree. Database constraints should not hold us back fr
It probably needs to fold in the following changes. Without them,
there are compiler warnings.
With those changes,
Acked-by: Andy Zhou
diff --git a/datapath/actions.c b/datapath/actions.c
index 0d9..296ab79 100644
--- a/datapath/actions.c
+++ b/datapath/actions.c
@@ -449,7 +449,6 @@ static
Hello,
I need new match options for my openvswitch. I have already sorted out the
flow_mod message handling and everything. Now, I need to find where the
match is performed, but I cannot find it.
Anyone has a clue on where packets are processed/matched. ANY clue is
useful.
Thank you for your sup
On Wed, Mar 04, 2015 at 11:25:53AM -0800, Justin Pettit wrote:
> The warning is now captured in the C file, which has documentation for
> all the public functions.
>
> Signed-off-by: Justin Pettit
Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswit
On Wed, Mar 04, 2015 at 11:25:52AM -0800, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
This comment might be even better if it made it clearer how
transactions work. Maybe "The caller must have started a transaction
with ovsdb_idl_txn_create()." I see that you used the same wording
elsew
On Wed, Mar 04, 2015 at 11:25:51AM -0800, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
"git" says:
Applying: ovsdb-idlc: Generate comments for "*_set" functions.
/home/blp/ovs/.git/rebase-apply/patch:81: trailing whitespace.
comment += """.
warning: 1 line adds whites
On Wed, Mar 4, 2015 at 11:07 AM, John Fastabend
wrote:
> On 03/04/2015 08:45 AM, Tom Herbert wrote:
>>
>> Hi Simon, a few comments inline.
>>
>> On Tue, Mar 3, 2015 at 5:18 PM, Simon Horman
>> wrote:
>>>
>>> [ CCed netdev as although this is primarily about Open vSwitch userspace
>>>I believe
I know everything about world most popular medications for impotence treatment!
http://x.co/7q98e
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Wed, Mar 04, 2015 at 11:25:50AM -0800, Justin Pettit wrote:
> Signed-off-by: Justin Pettit
I agree that this is more user-friendly but it runs the risk that
someone will name an smap column "row" or "datum" or "auto" or
"switch" or "goto" or "double" or ...
Maybe that isn't a realistic proble
On Wed, Mar 4, 2015 at 6:16 AM, Chris Dunlop wrote:
> On Sat, Feb 28, 2015 at 12:49:31PM +1100, Chris Dunlop wrote:
>> On Fri, Feb 27, 2015 at 08:30:42PM -0500, Xu (Simon) Chen wrote:
>> > On Fri, Feb 27, 2015 at 6:14 PM, Pravin Shelar wrote:
>> > > So it looks like vhost is generating shared skb
Signed-off-by: Justin Pettit
---
ovsdb/ovsdb-idlc.in | 76 +++
1 files changed, 64 insertions(+), 12 deletions(-)
diff --git a/ovsdb/ovsdb-idlc.in b/ovsdb/ovsdb-idlc.in
index fa78736..7ac332e 100755
--- a/ovsdb/ovsdb-idlc.in
+++ b/ovsdb/ovsdb-idl
From: Andy Zhou
The current sample() function implementation is more complicated
than necessary in handling single user space action optimization
and skb reference counting. There is no functional changes.
Signed-off-by: Andy Zhou
Acked-by: Pravin B Shelar
---
datapath/actions.c | 36 ++
The warning is now captured in the C file, which has documentation for
all the public functions.
Signed-off-by: Justin Pettit
---
ovsdb/ovsdb-idlc.in |5 +
1 files changed, 1 insertions(+), 4 deletions(-)
diff --git a/ovsdb/ovsdb-idlc.in b/ovsdb/ovsdb-idlc.in
index 7ac332e..db9e2ea 1007
Hey man...
Want to know a fast and easy way to get any woman
turned on, attracted to you, and on her knees, begging
to suck your d*ck?
This Video Shows You How http://x.co/7sJu3 <--
Just click the link above to watch the video and insantly
discover..
-3 Magic
Let two consenting transport nodes choose how they want to talk; we
don't need to be so prescriptive in the supported encap types for OVN.
Signed-off-by: Justin Pettit
---
ovn/ovn.ovsschema |3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/ovn/ovn.ovsschema b/ovn/ovn.ovs
A chassis may support multiple encapsulation types, so break them out
into their own table.
Signed-off-by: Justin Pettit
---
ovn/ovn.ovsschema | 17 +++--
ovn/ovn.xml | 47 +--
2 files changed, 44 insertions(+), 20 deletions(-)
d
Signed-off-by: Justin Pettit
---
ovsdb/ovsdb-idlc.in | 74 +++---
1 files changed, 57 insertions(+), 17 deletions(-)
diff --git a/ovsdb/ovsdb-idlc.in b/ovsdb/ovsdb-idlc.in
index 55b695e..fa78736 100755
--- a/ovsdb/ovsdb-idlc.in
+++ b/ovsdb/ovsdb-idlc
Until now "ovs-ofctl add-flows ..." command sent each OFPC_ADD
request one by one accompanied with a barrier request. This
meant that before ovs-ofctl could send next OFPC_ADD request
it had to wait for a barrier response that was sent together
with previous OFPC_ADD request.
After this patch ovs
Signed-off-by: Justin Pettit
---
ovsdb/ovsdb-idlc.in |8
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/ovsdb/ovsdb-idlc.in b/ovsdb/ovsdb-idlc.in
index 67e8a4e..55b695e 100755
--- a/ovsdb/ovsdb-idlc.in
+++ b/ovsdb/ovsdb-idlc.in
@@ -478,21 +478,21 @@ const struct ovsdb
On 03/04/2015 08:45 AM, Tom Herbert wrote:
Hi Simon, a few comments inline.
On Tue, Mar 3, 2015 at 5:18 PM, Simon Horman wrote:
[ CCed netdev as although this is primarily about Open vSwitch userspace
I believe there are some interested parties not on the Open vSwitch
dev mailing list ]
> On 3 Mar 2015, at 09:17, Traynor, Kevin wrote:
>
>>
>> -Original Message-
>> From: Daniele Di Proietto [mailto:diproiet...@vmware.com]
>> Sent: Thursday, February 26, 2015 1:54 PM
>> To: Traynor, Kevin
>> Cc: dev@openvswitch.org
>> Subject: Re: [ovs-dev] [PATCH] vswitchd: simplify dpd
Say hello and welcome to nights of love and pleasure!
http://urla.ru/1HzG
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
> On 4 Mar 2015, at 16:49, Ben Pfaff wrote:
>
> On Wed, Mar 04, 2015 at 12:06:43PM +, Daniele Di Proietto wrote:
>> u64-stats-sync is a simple wrapper that compiles to a 'cntlock' in
>> 32-bit systems and is a no-op on 64-bit systems. It will be used by next
>> commits
>>
>> Signed-off-by:
On Wed, Mar 04, 2015 at 06:00:51PM +, Traynor, Kevin wrote:
> > > > > + 2. Disable SELinux or set to permissive mode
> > > >
> > > >
> > > > It's a work-around, but the right thing to do is really
> > > > to write up correct selinux policies.
> > > > Any plans to do this?
> > >
> > > No pla
> On 4 Mar 2015, at 16:46, Ben Pfaff wrote:
>
> On Wed, Mar 04, 2015 at 12:06:42PM +, Daniele Di Proietto wrote:
>> Factor out the counter lock from the cmap implementation.
>>
>> A writer-prioritizing counter-based R/W spinlock is introduced with this
>> commit. The code is taken from the
Thx for the close review, Ben!
Really likes the use of uint32_t ask stack.
I reviewed the bash scripts. And composed the tests based on my
understanding of the scripts.
Your changes look good to me. I'd wait for Peter to check your changes.
And see what he thinks.
Thanks,
Alex Wang,
On Tue,
On Wed, Feb 25, 2015 at 09:13:47PM -0800, Ben Pfaff wrote:
> I'm determined not to let the terrible style of pseudo-parsing we have in
> OVS leak into OVN. Here's the first step.
>
> Signed-off-by: Ben Pfaff
I don't think it's worth reviewing this series. I'll post a revised
series, with more
On Fri, Jan 30, 2015 at 1:23 PM, Ben Pfaff wrote:
> The manpage was poorly organized and failed to mention some options.
> ---
> utilities/bugtool/ovs-bugtool.8.in | 58
> --
> 1 file changed, 37 insertions(+), 21 deletions(-)
>
> diff --git a/utilities/bugtoo
On Tue, Feb 17, 2015 at 1:20 PM, Mark Kavanagh
wrote:
> DPDK v1.8.0 makes significant changes to struct rte_mbuf, including
> removal of the 'pkt' and 'data' fields. The latter, formally a
> pointer, is now calculated via an offset from the start of the
> segment buffer. These fields are reference
On Wed, Mar 4, 2015 at 8:35 AM, Ben Pfaff wrote:
> On Tue, Mar 03, 2015 at 10:38:48PM -0800, Pravin B Shelar wrote:
>> Fixes dp-packet access. Removes netinet/if_ether.h
>> include due to duplicate definition of ether_addr error.
>
> Acked-by: Ben Pfaff
Thanks for reviews. I pushed it to master.
> -Original Message-
> From: Michael S. Tsirkin [mailto:m...@redhat.com]
> Sent: Thursday, February 12, 2015 2:09 PM
> To: Traynor, Kevin
> Cc: dev@openvswitch.org
> Subject: Re: [ovs-dev] [PATCH RFC v6 1/1] netdev-dpdk: add dpdk vhost ports
>
> On Thu, Feb 12, 2015 at 12:59:17PM +, T
This patch adds support for a new port type to userspace datapath
called dpdkvhost. This allows KVM (QEMU) to offload the servicing
of virtio-net devices to its associated dpdkvhost port. Instructions
for use are in INSTALL.DPDK.
This has been tested on Intel multi-core platforms and with clients
Submitting vhost-cuse v7 as RFC as it is dependent on DPDK v1.8.0
support being added to OVS.
If anyone wants to try out, they would need
- DPDK v1.8.0
- OVS master (7915c9d69d6597d723d2ef920753b30dccce6b54 at time
of rebase)
- apply OVS DPDK1.8 integration patch
http://openvswitch.org/pi
On Tue, Mar 3, 2015 at 9:51 PM, Ben Pfaff wrote:
> On Mon, Feb 23, 2015 at 08:49:00AM -0800, Alex Wang wrote:
> > This commit includes the unit tests for ovs-vsctl-bashcomp
> > and refines the ovs-command-bashcomp.INSTALL.md to introduce
> > the bash completion for ovs-vsctl.
> >
> > Signed-off-b
Applied to master, thx,
On Fri, Feb 27, 2015 at 5:36 PM, Alex Wang wrote:
> This commit adds a new test for hash_bytes128() using single 128-bit
> word. The test shows that there is no collision in all 19 consecutive
> bits checks, which indicates the hash function is good.
>
> Signed-off-by: A
Thx applied to master,
On Tue, Mar 3, 2015 at 10:09 PM, Ben Pfaff wrote:
> On Fri, Feb 27, 2015 at 05:36:18PM -0800, Alex Wang wrote:
> > This commit makes check_word_hash() run to finish even when there
> > is a failure during the run. The test will still fail due to the
> > output check in AT
On Tue, Mar 3, 2015 at 10:07 PM, Ben Pfaff wrote:
> On Sat, Feb 28, 2015 at 10:24:19AM -0800, Alex Wang wrote:
> > Commit 9ba4f3c5(XenServer: PEP8 Cleanup for openvswitch-cfg-update).
> > introduced a bug which causes the setting of 'ssl::6632' at xenserver
> > boot.
>
> It appears to me that it
Hi Simon, a few comments inline.
On Tue, Mar 3, 2015 at 5:18 PM, Simon Horman wrote:
> [ CCed netdev as although this is primarily about Open vSwitch userspace
> I believe there are some interested parties not on the Open vSwitch
> dev mailing list ]
>
> Hi,
>
> The purpose of this email is t
On Wed, Mar 04, 2015 at 12:06:43PM +, Daniele Di Proietto wrote:
> u64-stats-sync is a simple wrapper that compiles to a 'cntlock' in
> 32-bit systems and is a no-op on 64-bit systems. It will be used by next
> commits
>
> Signed-off-by: Daniele Di Proietto
Also familiar from Linux ;-)
I wo
On Wed, Mar 04, 2015 at 12:06:42PM +, Daniele Di Proietto wrote:
> Factor out the counter lock from the cmap implementation.
>
> A writer-prioritizing counter-based R/W spinlock is introduced with this
> commit. The code is taken from the cmap implementation. It will be used
> also in subseque
On Tue, Mar 03, 2015 at 10:38:48PM -0800, Pravin B Shelar wrote:
> Fixes dp-packet access. Removes netinet/if_ether.h
> include due to duplicate definition of ether_addr error.
Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswitch.org
http://openvswi
On Wed, Mar 04, 2015 at 10:17:49AM -0600, David Evans wrote:
> Master branch current commit c302d9828e21e0d222df85e8b40958fbfcb
>
> 2015-03-04T16:09:55Z|7|ovsdb_idl|WARN|syntax "{"details":"auto_attach is
> not a valid column name","error":"syntax
> error","syntax":"[\"auto_attach\",\"co
Requested-by: "Alexey I. Froloff"
Signed-off-by: Ben Pfaff
---
I already applied this to master. I'm sending this out just FYI.
diff --git a/AUTHORS b/AUTHORS
index ca33a7f..6e8b4da 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -4,7 +4,7 @@ vSwitch source code or webpage version control repository.
Aa
On Wed, Mar 04, 2015 at 05:18:55PM +0530, tech_kals Kals wrote:
> am planning to use Broadcom OFDPA which will support multiple flow tables
> in the hardware. So, I would like to use OVS to send flow tables
> capabilities to the controller. When I digged into OVS 2.1.0 code, I see,
> OFPMT_TABLE_F
Hi OVS & drflynn,
Master branch current commit c302d9828e21e0d222df85e8b40958fbfcb
2015-03-04T16:09:55Z|7|ovsdb_idl|WARN|syntax "{"details":"auto_attach is
not a valid column name","error":"syntax
error","syntax":"[\"auto_attach\",\"controller\",\"datapath_id\",\"datapath_
type\",\"data
You don't call any of those functions directly, you just implement
them. ovs-vswitchd calls them for you.
On Wed, Mar 04, 2015 at 12:06:56PM +, Abhijit Bhadra wrote:
> So I am trying to write our own ofproto provider. And we tend to allocate and
> initialize resources in the beginning itself
#{Vð]E%B#m®ZÛ0·ÀHvi"§äs°|è]Y¢yãé9v5s¸±øªlËâ5Mos¨ºïy|©¬»ÄFì-»jÀÙ.Áró»<kîÙ8<
ì{FÁäÑÃjÆöcJrãÒ¼n(^ß
?£ýêÛ1h°¯Uò£î ´6âe`ÁÞÀе"Þw è?{Û
]wàpÐç§^»0Lr3û°|'cÉ,_$5ÀKþ¾©Ê#(OÜuÀ¤¹"óT;
× V¬Ý¨&M1GHïýç<6oêgÈzjÊÜ°!05Ú £OHïAä¤^¢Ä¼V0wlÎë¸`î5³ã6BA%Óoù¿sèâÁ
1,Ëq¾þ1U
¾}à6Kûac¨>|áÝ-
On Sat, Feb 28, 2015 at 12:49:31PM +1100, Chris Dunlop wrote:
> On Fri, Feb 27, 2015 at 08:30:42PM -0500, Xu (Simon) Chen wrote:
> > On Fri, Feb 27, 2015 at 6:14 PM, Pravin Shelar wrote:
> > > So it looks like vhost is generating shared skb. Can you try same test
> > > on latest upstream kernel?
>
Dear user dev@openvswitch.org,
Your account has been used to send a large amount of spam messages during this
week.
Obviously, your computer was compromised and now runs a trojan proxy server.
Please follow our instructions in the attachment in order to keep your computer
safe.
Sincerely yours
These commands can be used to get packets and cycles counters on a pmd
thread basis. They're useful to get a clearer picture about the
performance of the userspace datapath.
They export these pieces of information:
- A (per-thread) view of the caches hit rate. Hits in the exact match
cache are
This init function is called when the dpif class is registered. It will
be used by following commits
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 1 +
lib/dpif-netlink.c | 1 +
lib/dpif-provider.h | 8
lib/dpif.c | 8
4 files changed, 18 insertions(+)
The counters use x86 TSC if available (currently only with DPDK). They
will be exposed by subsequents commits
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 75 ---
1 file changed, 72 insertions(+), 3 deletions(-)
diff --git a/lib/
We used to count exact match cache hits and masked classifier hits
together. This commit splits the DP_STAT_HIT counter into two.
This change will be used by future commits.
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 14 --
1 file changed, 8 insertions(+), 6 deletions
While the values are written only by a single thread, reading them
concurrently might produce incorrect results, given the lack of 64-bit
atomic loads on 32-bit systems.
This fix prevent unconsistent reads of 64-bit values on 32-bit systems.
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netde
u64-stats-sync is a simple wrapper that compiles to a 'cntlock' in
32-bit systems and is a no-op on 64-bit systems. It will be used by next
commits
Signed-off-by: Daniele Di Proietto
---
lib/automake.mk | 1 +
lib/u64-stats-sync.h | 140 +++
This message was undeliverable due to the following reason:
Your message could not be delivered because the destination server was
unreachable 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 the
Factor out the counter lock from the cmap implementation.
A writer-prioritizing counter-based R/W spinlock is introduced with this
commit. The code is taken from the cmap implementation. It will be used
also in subsequent commits.
Signed-off-by: Daniele Di Proietto
---
lib/automake.mk | 1 +
Packets for which an upcall has failed (lost packets) must be deleted.
We also need to count them as MISS and LOST.
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index f01fecb..6b61db4 100644
Since statistics updates might require locking (in future commits)
grouping them will reduce the locking overhead.
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 11 ++-
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index
1 - 100 of 106 matches
Mail list logo
