From: Paul Blakey
Those that we want to reuse in tc.c
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-linux.c | 164 +
lib/tc.c | 81
From: Paul Blakey
Using the new netdev flow api operate will now try and
offload flows to the relevant netdev of the input port.
Other operate methods flows will come in later patches.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
From: Paul Blakey
Flows offloaded to tc are identified by priority
and handle pair while OVS flows are identified by ufid.
Added a hash map to convert between the two for later
retrieval and deleting of offloaded flows.
Signed-off-by: Paul Blakey
From: Paul Blakey
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/automake.mk | 2 +
lib/netdev-bsd.c | 2 +
lib/netdev-dpdk.c| 1 +
lib/netdev-dummy.c | 2 +
lib/netdev-linux.c |
From: Paul Blakey
Add a new configuration option - hw-offload that enables netdev
flow api. Enabling this option will allow offloading flows
using netdev implementation instead of the kernel datapath.
This configuration option defaults to false - disabled.
Signed-off-by:
From: Paul Blakey
Search the requested ufid for a offloaded flow, and if found,
dump and parse it back to required format.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-tc-offloads.c | 49
This is a follow up patch to document the systemd behavior including
the change introduced by the "rhel-systemd: Restart openvswitch
service if a daemon crashes", still under review.
Signed-off-by: Eelco Chaudron
---
rhel/README.RHEL.rst | 33
Signed-off-by: Ben Pfaff
---
lib/jsonrpc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/jsonrpc.h b/lib/jsonrpc.h
index 5f46e3b..982017a 100644
--- a/lib/jsonrpc.h
+++ b/lib/jsonrpc.h
@@ -125,7 +125,7 @@ void jsonrpc_session_enable_reconnect(struct
This patch series introduces rule offload functionality to dpif-netlink
via netdev ports new flow offloading API. The user can specify whether to
enable rule offloading or not via OVS configuration. Netdev providers
are able to implement netdev flow offload API in order to offload rules.
This
From: Paul Blakey
Add a new configuration tc-policy option that controls tc
flower flag. Possible options are none, skip_sw, skip_hw.
The default is none which is to insert the rule both to sw and hw.
This option is only relevant if hw-offload is enabled.
Signed-off-by: Paul
From: Paul Blakey
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-tc-offloads.c | 23 ++-
1 file changed, 22 insertions(+), 1 deletion(-)
diff --git a/lib/netdev-tc-offloads.c
From: Paul Blakey
While dumping flows, dump flows that were offloaded to
netdev and parse them back to dpif flow.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/dpif-netlink.c | 178
Testcase 1057 ofproto-dpif - fragment handling - upcall reports
the following leak:
xrealloc (util.c:123)
vconn_dump_flows (vconn.c:1030)
read_flows_from_switch (ovs-ofctl.c:3360)
ofctl_replace_flows (ovs-ofctl.c:3433)
ovs_cmdl_run_command__ (command-line.c:115)
Signed-off-by: William
From: Paul Blakey
If netdev flow offloading is enabled, flush all
added ports using netdev flow api.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/dpif-netlink.c | 5 +
lib/netdev.c | 44
From: Paul Blakey
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-tc-offloads.c | 14 --
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/lib/netdev-tc-offloads.c b/lib/netdev-tc-offloads.c
From: Paul Blakey
If a flow was offloaded to a netdev we delete it using netdev
flow api.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/dpif-netlink.c | 12 +++-
lib/netdev.c | 15 +++
2 files
From: Paul Blakey
Added compatibility headers for actions vlan and tunnel key.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
acinclude.m4 | 26 ++
configure.ac | 1 +
Nos gustaría hacerle una grata invitación a adquirir nuestra Póliza de
Capacitación Indispensable para los Responsables de Ventas.
No deje pasar la oportunidad de poner esta exclusiva colección a trabajar en
benecio de su empresa y sus equipos de trabajo… Consulte la programación y
compruebe
Valgrind testcase 772: appctl - route/lookup6 reports the
following definitely lost:
xmalloc (util.c:112)
miniflow_alloc (flow.c:2500)
minimatch_init (match.c:1387)
rt_entry_delete (ovs-router.c:274)
ovs_router_del (ovs-router.c:384)
process_command (unixctl.c:313)
Signed-off-by:
From: Paul Blakey
Usage:
# to dump all datapath flows (default):
ovs-dpctl dump-flows
# to dump only flows that in kernel datapath:
ovs-dpctl dump-flows type=ovs
# to dump only flows that are offloaded:
ovs-dpctl dump-flows type=offloaded
From: Paul Blakey
The new system-offloads-testsuite, which can be launched via
`make check-offloads`, tests offloading capabilities
to makes sure that certian flows are actually offloaded.
The tests run on virtual netdevices (VETH).
Signed-off-by: Paul Blakey
This fixes a memory leak, although it was not a significant leak because
the symbol table is in use until shortly before ovn-controller exits.
Reported-by: William Tu
Signed-off-by: Ben Pfaff
---
ovn/controller/ofctrl.c | 1 +
1 file changed, 1 insertion(+)
From: Paul Blakey
Add tc flower interface that will be used to offload flows via tc
flower classifier. Depending on the flag used (skip_sw/hw) flower
will pass those to HW or handle them itself.
Co-authored-by: Shahar Klein
Signed-off-by: Shahar Klein
From: Paul Blakey
To use netdev flow offloading api, dpifs needs to iterate over
added ports. This addition inserts the added dpif ports in a hash map,
The map will also be used to translate dpif ports to netdevs.
Signed-off-by: Paul Blakey
Reviewed-by:
From: Paul Blakey
Flower classifer requires a different priority per mask,
so we hash the mask and generate a new priority for
each new mask used.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-tc-offloads.c | 38
From: Paul Blakey
We want to use this later in the HW offloading implementation
which we currently also support Linux only.
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
lib/netdev-linux.c | 7 +++
lib/netdev-linux.h |
From: Paul Blakey
netdev vports are backed by actualy netdev at the kernel
level, so they can use the common netdev-tc offloads interface
for flow offloading (if enabled).
Signed-off-by: Paul Blakey
Reviewed-by: Roi Dayan
---
Hello,
Good day to you!
This is Mark; I'm writing to check if you would be interested to acquire the
newly released Business Database with verified emails and complete contact
information.
Major Industrial List:- Agriculture, Business Services, Chambers of
Commerce, Cities, Towns &
thanks! I tested it and found no problem.
On Wed, Feb 8, 2017 at 8:40 AM, Ben Pfaff wrote:
> This fixes a memory leak, although it was not a significant leak because
> the symbol table is in use until shortly before ovn-controller exits.
>
> Reported-by: William Tu
On Wed, Feb 08, 2017 at 06:27:59PM +0800, lg.yue wrote:
> Ben Pfaff, Hi:
> i have to make it clear that QoS here refers to bandwidth
> limitation(TC), rather than dscp or tos. what i want to do is to limit the
> bandwidth of vif and ovn's router port.
> allocate_chassis_queueid and
Acked-By: Shashank Ram
From: ovs-dev-boun...@openvswitch.org on
behalf of Alin Serdean
Sent: Tuesday, February 7, 2017 10:41:24 PM
To: d...@openvswitch.org
Subject: [ovs-dev]
On 7 February 2017 at 22:41, Alin Serdean
wrote:
> The netdev Windows construct uses query_netdev to see if a port exists
> in the datapath, in the case an error occurred in the reply message
> we returned 0, meaning netdev_open was successful.
>
> This patch
Thanks, applied to master and branch-2.7.
On Wed, Feb 08, 2017 at 10:46:29AM -0800, William Tu wrote:
> thanks! I tested it and found no problem.
>
> On Wed, Feb 8, 2017 at 8:40 AM, Ben Pfaff wrote:
> > This fixes a memory leak, although it was not a significant leak because
> >
On Wed, Feb 8, 2017 at 8:32 AM, Ben Pfaff wrote:
> This is convenient in expressions, e.g. "uuid = x ? *x : UUID_ZERO;".
>
> Signed-off-by: Ben Pfaff
Acked-by: Andy Zhou
___
dev mailing list
On Wed, Feb 8, 2017 at 8:32 AM, Ben Pfaff wrote:
> Signed-off-by: Ben Pfaff
Acked-by: Andy Zhou
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On Wed, Feb 08, 2017 at 11:24:28AM -0800, Andy Zhou wrote:
> On Wed, Feb 8, 2017 at 7:03 AM, William Tu wrote:
> > Testcase 1057 ofproto-dpif - fragment handling - upcall reports
> > the following leak:
> > xrealloc (util.c:123)
> > vconn_dump_flows (vconn.c:1030)
> >
On Wed, Feb 08, 2017 at 11:29:19AM -0800, Andy Zhou wrote:
> On Wed, Feb 8, 2017 at 8:32 AM, Ben Pfaff wrote:
> > This is convenient in expressions, e.g. "uuid = x ? *x : UUID_ZERO;".
> >
> > Signed-off-by: Ben Pfaff
> Acked-by: Andy Zhou
Thanks for
On Wed, Feb 8, 2017 at 7:03 AM, William Tu wrote:
> Valgrind testcase 772: appctl - route/lookup6 reports the
> following definitely lost:
> xmalloc (util.c:112)
> miniflow_alloc (flow.c:2500)
> minimatch_init (match.c:1387)
> rt_entry_delete (ovs-router.c:274)
>
On Wed, Feb 8, 2017 at 8:32 AM, Ben Pfaff wrote:
> Signed-off-by: Ben Pfaff
Acked-by: Andy Zhou
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On Tue, Feb 07, 2017 at 08:40:21PM -0800, Andy Zhou wrote:
> Currently, there is no way for an OVSDB server to ID itself. This patch
> adds a UUID field that is populated every time OVSDB server runs.
> Later patch will make use this UUID to detect and stop and OVSDB server
> from replicating
On Wed, Feb 8, 2017 at 3:25 PM, Ben Pfaff wrote:
> On Wed, Feb 08, 2017 at 03:15:51PM -0800, Andy Zhou wrote:
>> On Wed, Feb 8, 2017 at 11:40 AM, Ben Pfaff wrote:
>> > In replication_init(), I'd use "=" to copy the uuid, instead of
>> > memcpy().
>> >
>> O.K. I will
On Wed, Feb 8, 2017 at 11:40 AM, Ben Pfaff wrote:
> On Tue, Feb 07, 2017 at 08:40:22PM -0800, Andy Zhou wrote:
>> Replication OVSDB server from itself is usually caused by configuration
>> errors. Such configuration errors can lead to OVSDB server data loss.
>> See "reported-at" for
On Wed, Feb 8, 2017 at 11:40 AM, Ben Pfaff wrote:
> On Wed, Feb 08, 2017 at 11:24:28AM -0800, Andy Zhou wrote:
>> On Wed, Feb 8, 2017 at 7:03 AM, William Tu wrote:
>> > Testcase 1057 ofproto-dpif - fragment handling - upcall reports
>> > the following leak:
>> >
On Wed, Feb 08, 2017 at 03:15:51PM -0800, Andy Zhou wrote:
> On Wed, Feb 8, 2017 at 11:40 AM, Ben Pfaff wrote:
> > In replication_init(), I'd use "=" to copy the uuid, instead of
> > memcpy().
> >
> O.K. I will use the brand spanking new UUID_ZERO!
I was really just expecting
The following commit has provided a fix upstream to Linux but the fix has not
made its way into the OVS tree's backport yet:
75f01a4c9cc2 ("openvswitch: maintain correct checksum state in conntrack
actions")
In the interests of providing all available fixes for v2.7 prior to release, I
propose
Upstream commit:
openvswitch: maintain correct checksum state in conntrack actions
When executing conntrack actions on skbuffs with checksum mode
CHECKSUM_COMPLETE, the checksum must be updated to account for
header pushes and pulls. Otherwise we get "hw csum failure"
logs
Signed-off-by: Joe Stringer
---
datapath/linux/compat/include/linux/netdevice.h | 5 --
datapath/linux/compat/netdevice.c | 71 -
2 files changed, 76 deletions(-)
diff --git a/datapath/linux/compat/include/linux/netdevice.h
Good day
I came to know from some
trusted sources of your company produce high quality product and would
very much like to learn more about it. I would appreciate if you can
send any information that could help me in my selection process.
Please
elaborate on the various options along with
On 8 February 2017 at 02:08, Ian Stokes wrote:
> Clarify that the use of the user space datapath with non DPDK devices is
> considered experimental.
>
> Fixes: 602e24ee189b (doc: Remove experimental warning for DPDK.)
> Signed-off-by: Ian Stokes
>
On 7 February 2017 at 21:15, Yang, Yi Y wrote:
> Joe, I investigated all the patches which changed include/linux/if_vlan.h for
> 802.1ad in net-next again, I found ovs compat mode doesn't need most of them
> at all, datapath/linux/compat/include/linux/ only includes part of
Then, are you merging
https://mail.openvswitch.org/pipermail/ovs-dev/2017-February/328492.html or do
I need to do anything else for it?
-Original Message-
From: Joe Stringer [mailto:j...@ovn.org]
Sent: Thursday, February 9, 2017 9:44 AM
To: Yang, Yi Y
Cc: ovs dev
On 7 February 2017 at 20:55, Yang, Yi wrote:
> On Tue, Feb 07, 2017 at 02:30:46PM -0800, Joe Stringer wrote:
>> On 7 February 2017 at 09:44, Joe Stringer wrote:
>> > On 6 February 2017 at 16:46, Yang, Yi Y wrote:
>> >> Joe, I checked
Ben Pfaff, Hi:
i am clear now. thanks.
i have another two questions to ask.
1. how to limit port's ingress bandwidth?
2. i have moved a port to namespace vm1, and ovs-vsctl set interface
9129f3da-b074-4707-a499-f728e0c8e5e1 ingress_policing_rate=8. but its bandwidth
is not limited by this
Signed-off-by: Darrell Ball
---
NEWS | 2 ++
1 file changed, 2 insertions(+)
diff --git a/NEWS b/NEWS
index aebd99c..890549f 100644
--- a/NEWS
+++ b/NEWS
@@ -3,6 +3,8 @@ Post-v2.7.0
- Tunnels:
* Added support to set packet mark for tunnel endpoint using
Signed-off-by: Darrell Ball
---
tests/system-userspace-macros.at | 7 ++-
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/tests/system-userspace-macros.at b/tests/system-userspace-macros.at
index 631f71a..6e3d468 100644
--- a/tests/system-userspace-macros.at
> On 7 February 2017 at 12:22, Stokes, Ian wrote:
> >> On 6 February 2017 at 09:20, Ian Stokes wrote:
> >> > Remove the experimental warning tag in documentation regarding OVS
> >> > deployed with DPDK.
> >> >
> >> > Signed-off-by: Ian Stokes
Signed-off-by: Darrell Ball
---
lib/packets.c | 2 +-
lib/packets.h | 4
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/lib/packets.c b/lib/packets.c
index fa70df6..94e7d87 100644
--- a/lib/packets.c
+++ b/lib/packets.c
@@ -986,7 +986,7 @@
This patch series introduces NAT support for the userspace datapath.
The per packet scope of lookups for NAT and un_NAT is at
the bucket level rather than global. One hash table is
introduced to support create/delete handling. The create/delete
events may be further optimized, if the need becomes
Signed-off-by: Darrell Ball
---
lib/conntrack.c | 49 ++---
1 file changed, 10 insertions(+), 39 deletions(-)
diff --git a/lib/conntrack.c b/lib/conntrack.c
index 0a611a2..ee515a0 100644
--- a/lib/conntrack.c
+++ b/lib/conntrack.c
@@
Clarify that the use of the user space datapath with non DPDK devices is
considered experimental.
Fixes: 602e24ee189b (doc: Remove experimental warning for DPDK.)
Signed-off-by: Ian Stokes
Co-authored-by: Joe Stringer
---
README.rst |4 ++--
1 files
Ben Pfaff, Hi:
i have to make it clear that QoS here refers to bandwidth limitation(TC),
rather than dscp or tos. what i want to do is to limit the bandwidth of vif
and ovn's router port.
allocate_chassis_queueid and dpif_queue_to_priority tell that queue_id is
a incremental
On Tue, Feb 07, 2017 at 09:18:23PM +, Bhanuprakash Bodireddy wrote:
> List details of various popular distributions shipping Open vSwitch
> packages. Also include the information of the distros supporting DPDK
> accelerated datapath.
>
> Signed-off-by: Bhanuprakash Bodireddy
yes, thanks.
I will introduce cls_rule_destroy() and free the minimatch inside.
--William
On Tue, Feb 7, 2017 at 11:33 PM, Andy Zhou wrote:
> On Tue, Feb 7, 2017 at 10:41 PM, William Tu wrote:
>> Valgrind testcase 772: appctl - route/lookup6 reports the
>>
Hi all,
This L3 patchset looks similar to what we did internally with OVS 2.6 to
add support for IPv6 tunnels.
Could you please confirm that ovs-dpctl reports correct statistics with
this patchset when one uses in-kernel Linux datapath? We had some issues
with this (the counters were always
64 matches
Mail list logo