On Sat, May 26, 2018 at 11:16:42AM +0800, Liu Bo wrote:
> > +/*
> > + * Returns pointer to the specified byte @offset within @radix, allocating
> > it if
> > + * necessary - newly allocated slots are always zeroed out:
> > + */
> > +void *__genradix_ptr_alloc(struct __genradix *radix, size_t
Hi Kent,
(Add all ML to cc this time.)
On Wed, May 23, 2018 at 9:18 AM, Kent Overstreet
wrote:
> Very simple radix tree implementation that supports storing arbitrary
> size entries, up to PAGE_SIZE - upcoming patches will convert existing
> flex_array users to
Ihre Gewinne wurden verarbeitet und es ist bereit für die Übertragung an Sie,
also kontaktieren Sie mich so schnell wie möglich, um es zu erhalten.
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
All of these releases seem fine to me.
Acked-by: Ben Pfaff
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Signed-off-by: Justin Pettit
---
NEWS | 3 ++-
debian/changelog | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/NEWS b/NEWS
index 06f4a6475f81..452d0dd0bb02 100644
--- a/NEWS
+++ b/NEWS
@@ -1,5 +1,6 @@
-v2.9.2 - xx xxx
+v2.9.2 - 25 May
Signed-off-by: Justin Pettit
---
NEWS | 3 +++
configure.ac | 2 +-
debian/changelog | 6 ++
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/NEWS b/NEWS
index 452d0dd0bb02..622c230ae5b0 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,6 @@
+v2.9.3 - xx
Signed-off-by: Justin Pettit
---
NEWS | 3 +++
configure.ac | 2 +-
debian/changelog | 6 ++
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/NEWS b/NEWS
index 047f8751bfab..101ded1ddca0 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,6 @@
+v2.8.5 - xx
Signed-off-by: Justin Pettit
---
NEWS | 6 +++---
debian/changelog | 6 +++---
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/NEWS b/NEWS
index c8b5659e363c..047f8751bfab 100644
--- a/NEWS
+++ b/NEWS
@@ -1,6 +1,6 @@
-v2.8.4 - xx xxx
Signed-off-by: Justin Pettit
---
NEWS | 4 ++--
debian/changelog | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/NEWS b/NEWS
index f4046baa5a76..2a469b7df446 100644
--- a/NEWS
+++ b/NEWS
@@ -1,5 +1,5 @@
-v2.7.6 - xx xxx
Signed-off-by: Justin Pettit
---
NEWS | 3 +++
configure.ac | 2 +-
debian/changelog | 6 ++
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/NEWS b/NEWS
index 2a469b7df446..aa1e476f3557 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,6 @@
+v2.7.7 - xx
Signed-off-by: Justin Pettit
---
NEWS | 3 +++
configure.ac | 2 +-
debian/changelog | 6 ++
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/NEWS b/NEWS
index 7fec7dc3db51..dcef1e73a199 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,6 @@
+v2.6.4 - xx
Signed-off-by: Justin Pettit
---
NEWS | 5 +++--
debian/changelog | 2 +-
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/NEWS b/NEWS
index efbae2aced3b..7fec7dc3db51 100644
--- a/NEWS
+++ b/NEWS
@@ -1,5 +1,6 @@
-v2.6.3 - xx xxx
On Thu, May 17, 2018 at 01:16:55PM -0400, Mark Michelson wrote:
> When inserting data into a "singleton" table (one that has maxRows ==
> 1), there is a check that ensures that the table is currently empty
> before inserting the row. The intention is to prevent races where
> multiple clients might
On Thu, May 24, 2018 at 05:27:58PM +0200, Jan Scheurich wrote:
> The current default OpenFlow select group implementation sends every new L4
> flow
> to the slow path for the balancing decision and installs a 5-tuple "miniflow"
> in the datapath to forward subsequent packets of the connection
On Thu, May 24, 2018 at 10:20:26PM -0700, Justin Pettit wrote:
>
> > On May 18, 2018, at 2:37 PM, Ben Pfaff wrote:
> >
> > Signed-off-by: Ben Pfaff
>
> Acked-by: Justin Pettit
Thanks for all the reviews. I applied your suggestions and then
OK.
On Fri, May 25, 2018 at 03:46:31AM +, Lilijun (Jerry, Cloud Networking)
wrote:
> Hi Ben,
>
>Thanks for your reply very much.
>
>Currently, if we delete a port, ovs only flush the related datapath flows.
>
>So I have an opinions as follows:
>When deleting the ovs
On Thu, May 24, 2018 at 04:46:01PM -0700, Justin Pettit wrote:
>
> > On May 23, 2018, at 4:39 PM, Ben Pfaff wrote:
> >
> > Signed-off-by: Ben Pfaff
>
> Acked-by: Justin Pettit
Thanks, applied to master.
On Thu, May 24, 2018 at 05:23:03PM -0700, Justin Pettit wrote:
>
> > On May 18, 2018, at 2:37 PM, Ben Pfaff wrote:
> >
> > diff --git a/Documentation/conf.py b/Documentation/conf.py
> > index babda21defff..d81fcaeb440d 100644
> > --- a/Documentation/conf.py
> > +++
On Thu, May 24, 2018 at 05:01:48PM -0700, Justin Pettit wrote:
>
> > On May 18, 2018, at 2:37 PM, Ben Pfaff wrote:
> >
> > This test is supposed to be parameterized, but one of the loops didn't
> > honor the parameterization and just had hardcoded values. Also, the
> > output
On Thu, May 24, 2018 at 04:41:38PM -0700, Justin Pettit wrote:
>
> > On May 24, 2018, at 11:00 AM, Ben Pfaff wrote:
> >
> > We've actually made a lot of improvements.
> >
> > Signed-off-by: Ben Pfaff
>
> Acked-by: Justin Pettit
Thanks, applied
On Fri, May 25, 2018 at 06:28:49AM -0700, William Tu wrote:
> Clean up the duplicate definition of OVS_VPORT_TYPE_ERSPAN
> since it is defined in openvswitch.h.
>
> Cc: Greg Rose
> Signed-off-by: William Tu
Applied to master, thanks!
(Maybe I should
On Fri, May 25, 2018 at 06:28:48AM -0700, William Tu wrote:
> Instead of memcpy to a local stack, parse the erspan
> metadata in memory.
>
> Suggested-by: Ben Pfaff
> Signed-off-by: William Tu
Thanks, applied to master.
On Fri, May 25, 2018 at 09:47:20AM -0700, William Tu wrote:
> Update Documentation/faq/configuration.rst about ERSPAN
> and Update NEWS.
>
> Cc: Greg Rose
> Signed-off-by: William Tu
Thanks! Applied to master.
On Fri, May 25, 2018 at 11:15:10PM +0300, aserd...@ovn.org wrote:
> > > On May 24, 2018, at 10:32 AM, Ben Pfaff wrote:
> > >
> > > Several OVS structs contain embedded named unions, like this:
> > >
> > > struct {
> > >...
> > >union {
> > >...
> > >} u;
> > > };
On Thu, May 24, 2018 at 10:32:50PM -0700, Justin Pettit wrote:
>
> > On May 18, 2018, at 10:16 AM, Ben Pfaff wrote:
> >
> > Signed-off-by: Ben Pfaff
>
> Acked-by: Justin Pettit
Thanks for the reviews. I applied these patches to master.
On Fri, May 25, 2018 at 08:03:18AM -0700, William Tu wrote:
> ERSPAN is the first real-world use cases of Experimenter OXM,
> which introduces 4 new NXOXM_ET_ fields (ver, idx, dir, hwid).
> The patch adds test cases for these fields.
>
> Cc: Greg Rose
> Signed-off-by:
> > On May 24, 2018, at 10:32 AM, Ben Pfaff wrote:
> >
> > Several OVS structs contain embedded named unions, like this:
> >
> > struct {
> >...
> >union {
> >...
> >} u;
> > };
> >
> > C11 standardized a feature that many compilers already implemented
> >
Sounds good. I'll take it from here. Thanks.
--Justin
> On May 25, 2018, at 12:05 PM, Stokes, Ian wrote:
>
>> Sure. No problem.
>
> Thanks Justin,
>
> The bug fixes have now been merged to the release branches and are ready to
> go. Thanks again for helping with
> Sure. No problem.
Thanks Justin,
The bug fixes have now been merged to the release branches and are ready to go.
Thanks again for helping with this, is there anything else you need from my
side?
Regards
Ian
>
> --Justin
>
>
> > On May 23, 2018, at 1:59 AM, Stokes, Ian
> Thanks for all the release branch updates. I merged all of them into the
> respective branches.
Thanks for the quick merge Ben, much appreciated.
Ian
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On Thu, May 17, 2018 at 6:04 AM, wrote:
> From: Numan Siddique
>
> When a node 'A' in the pacemaker cluster running OVN db servers in master is
> brought down ungracefully ('echo b > /proc/sysrq_trigger' for example),
> pacemaker
> is not able to
On Fri, May 25, 2018 at 05:56:51AM -0700, William Tu wrote:
> >
> > OK, now I understand what's going on. This is only used to define the
> > format of the OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS attribute. Since it's not
> > a wire format at all, we don't need to use ovs_16aligned_be32 either,
> > and
Thanks for all the release branch updates. I merged all of them into
the respective branches.
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On Fri, May 25, 2018 at 02:17:40PM +, Stokes, Ian wrote:
> Hi Ben,
>
> The following changes since commit 55b259471719ceca1f0083bdd6a5f8c3e7690bae:
>
> Extend tests for conjunctive match support in OVN (2018-05-24 11:23:58
> -0700)
>
> are available in the git repository at:
>
>
On 05/25/2018 05:53 PM, Lam, Tiago wrote:
>> VLOG_ERR("Failed mempool \"%s\" create request of %u mbufs",
>> mp_name, n_mbufs);
>> }
> Just a thought, but now with shared memory where n_mbufs are initially
> set to 4096*64, one can see this error log
Hi Tiago,
On 05/25/2018 05:53 PM, Lam, Tiago wrote:
> Hi Ian,
>
> Thanks for bringing this forward.
>
> I've tested this on current master by re-configuring MTUs of existing
> ports, adding new ports, deleting existing ones, etc. It seems to be
> behaving as expected:
> - On the shared model,
Hi Ian,
Thanks for bringing this forward.
I've tested this on current master by re-configuring MTUs of existing
ports, adding new ports, deleting existing ones, etc. It seems to be
behaving as expected:
- On the shared model, it allocates a new mempool only if the MTU
changes, otherwise reuses
Update Documentation/faq/configuration.rst about ERSPAN
and Update NEWS.
Cc: Greg Rose
Signed-off-by: William Tu
---
Documentation/faq/configuration.rst | 20 ++--
NEWS| 5 +
2 files changed, 23
Hi Ian,
I did all my testing with DPDK 17.11.2 and the following OVS commit (HEAD of
master at the time of testing):
cferrite@silpixa00393943:~/ovs$ git show --summary
commit 55b259471719ceca1f0083bdd6a5f8c3e7690bae
Author: Numan Siddique
Date: Thu May 24 17:45:53 2018
On 25.05.2018 17:39, Eelco Chaudron wrote:
> On 25/05/18 15:30, Ilya Maximets wrote:
>>> When ping-pong'in a live VM migration between two machines running
>>> OVS-DPDK every now and then the ping misses would increase
>>> dramatically. For example:
>>>
>>> ===Stream Rate: 3Mpps===
ERSPAN is the first real-world use cases of Experimenter OXM,
which introduces 4 new NXOXM_ET_ fields (ver, idx, dir, hwid).
The patch adds test cases for these fields.
Cc: Greg Rose
Signed-off-by: William Tu
---
tests/ovs-ofctl.at | 61
On 25/05/18 15:30, Ilya Maximets wrote:
When ping-pong'in a live VM migration between two machines running
OVS-DPDK every now and then the ping misses would increase
dramatically. For example:
===Stream Rate: 3Mpps===
No Stream_Rate Downtime Totaltime Ping_Loss Moongen_Loss
0
Hi Ben,
The following changes since commit acc46dc06e02316c27b9a5d66ac85726c2091a6a:
Prepare for 2.6.3. (2018-05-18 15:53:55 -0700)
are available in the git repository at:
https://github.com/istokes/ovs dpdk_merge_2_6
for you to fetch changes up to
Hi Ben,
The following changes since commit 3c21d3f679aa980aeed79bd5582d891b9f109fe6:
Prepare for 2.7.6. (2018-05-18 15:54:21 -0700)
are available in the git repository at:
https://github.com/istokes/ovs dpdk_merge_2_7
for you to fetch changes up to
Hi Ben,
The following changes since commit 8b10a2632b84cfe5153203db9d042d51864af328:
datapath: compat: Fix ndo_size in RHEL 7.5 backport (2018-05-23 15:36:00
-0700)
are available in the git repository at:
https://github.com/istokes/ovs dpdk_merge_2_8
for you to fetch changes up to
Hi Ben,
The following changes since commit 2a3ee45583ef3880da99fd415410b71054f7711a:
datapath: compat: Fix ndo_size in RHEL 7.5 backport (2018-05-23 15:35:36
-0700)
are available in the git repository at:
https://github.com/istokes/ovs dpdk_merge_2_9
for you to fetch changes up to
Hi Ben,
The following changes since commit 55b259471719ceca1f0083bdd6a5f8c3e7690bae:
Extend tests for conjunctive match support in OVN (2018-05-24 11:23:58 -0700)
are available in the git repository at:
https://github.com/istokes/ovs dpdk_merge
for you to fetch changes up to
On Wed, May 23, 2018 at 11:50 PM, rakesh kumar wrote:
> Dear team,
>
> Please share your experience of OVS in userspace, I am trying to configure
> OVS in userspace and want to skip the Kernel module so that the packet
> processing and switching can only be handled in
On Fri, May 25, 2018 at 12:58 AM, rakesh kumar wrote:
> Hello Team
>
> I am planning to write few algorithms to modify the switching behavior of
> packets by ovs switch but I don’t want to do in kernel mode , I want my
> entire process to be handled in userspace .
>
>
> When ping-pong'in a live VM migration between two machines running
> OVS-DPDK every now and then the ping misses would increase
> dramatically. For example:
>
> ===Stream Rate: 3Mpps===
> No Stream_Rate Downtime Totaltime Ping_Loss Moongen_Loss
> 0 3Mpps 128
Clean up the duplicate definition of OVS_VPORT_TYPE_ERSPAN
since it is defined in openvswitch.h.
Cc: Greg Rose
Signed-off-by: William Tu
---
datapath/linux/compat/ip_gre.c | 4
1 file changed, 4 deletions(-)
diff --git
Instead of memcpy to a local stack, parse the erspan
metadata in memory.
Suggested-by: Ben Pfaff
Signed-off-by: William Tu
---
lib/odp-util.c | 13 +
1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/lib/odp-util.c b/lib/odp-util.c
>
> OK, now I understand what's going on. This is only used to define the
> format of the OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS attribute. Since it's not
> a wire format at all, we don't need to use ovs_16aligned_be32 either,
> and an "int" is fine too.
>
> Since erspan_metadata is part of the kernel
Hi,
I did all my testing with DPDK 17.11.2 and the following OVS commit (patch
doesn't apply cleanly to master):
cferrite@silpixa00393943:~/ovs$ git show --summary
commit 6b71df2fc06921758798e41833d67d9daf647d19
Author: Kevin Traynor
Date: Wed Apr 25 12:20:53 2018 +0100
From: venkata anil
When a vm on a vlan tenant network sends traffic to an external network,
it is tunneled from host chassis to gateway chassis. In the earlier
discussion [1], Russel (also in his doc [2]) suggested if we can figure
out a way for OVN to do this redirect to
On 05/18/2018 03:30 PM, Ian Stokes wrote:
> This commit re-introduces the concept of shared mempools as the default
> memory model for DPDK devices. Per port mempools are still available but
> must be enabled explicitly by a user.
>
> OVS previously used a shared mempool model for ports with the
When ping-pong'in a live VM migration between two machines running
OVS-DPDK every now and then the ping misses would increase
dramatically. For example:
===Stream Rate: 3Mpps===
No Stream_Rate Downtime Totaltime Ping_Loss Moongen_Loss
0 3Mpps 128 13974 115
On Thu, May 24, 2018 at 2:16 PM, Ben Pfaff wrote:
> On Thu, May 24, 2018 at 12:08:31PM -0700, William Tu wrote:
> > On Thu, May 24, 2018 at 10:20 AM, Ben Pfaff wrote:
> > > On Thu, May 24, 2018 at 05:36:10AM -0700, William Tu wrote:
> > >> On Wed, May 23, 2018 at
Team ,
Anyone tried to use OVS as a SDN services in Core Network emulator ,
Please share your findings !
Regards
Rakesh Kumar
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Hello Team
I am planning to write few algorithms to modify the switching behavior of
packets by ovs switch but I don’t want to do in kernel mode , I want my entire
process to be handled in userspace .
Team waiting for your suggestions!!
Regards
Rakesh Kumar
Hello everyone,
May I ask to provide some (even brief) documentation about each specific
drop counter?
That would really help understanding why a specific drop is happening.
Thanks,
Federico
On 25 May 2018 at 07:44, Rohith Basavaraja
wrote:
> Hi Greg,
>
>
61 matches
Mail list logo