After the hotplug of DPDK ports, a valid dpdk-devargs must be
specified. Otherwise, the DPDK device can't be available.
Signed-off-by: Binbin Xu
---
Documentation/faq/configuration.rst | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git
Not a complete review. This code is full of races.
See details inline.
Best regards, Ilya Maximets.
On 17.01.2017 18:37, antonio.fische...@intel.com wrote:
> This patch implements the intermediate Tx queues on 'dpdk' type ports.
>
> Test results:
> * In worst case scenario with fewer packets
2017-01-17 11:43 GMT-08:00 Kevin Traynor :
> On 01/17/2017 05:43 PM, Ciara Loftus wrote:
>> Instead of counting all polling cycles as processing cycles, only count
>> the cycles where packets were received from the polling.
>
> This makes these stats much clearer. One minor
Make sense, will change it in v3.
-Original Message-
From: Jiri Benc [mailto:jb...@redhat.com]
Sent: Wednesday, January 18, 2017 12:37 AM
To: Yang, Yi Y
Cc: d...@openvswitch.org
Subject: Re: [ovs-dev] [PATCH v2 15/17] datapath: enable vxlangpe creation in
compat
Do we need to convert the tunKey->dst_port to network byte order?
On 1/10/17, 8:48 AM, "ovs-dev-boun...@openvswitch.org on behalf of Alin
Serdean" wrote:
>Change the UDP destination port(VXLAN header) to check if
We should consolidate this logic into 1 function for retrieving the tunKey from
attr. This can be done separately.
Acked-by: Sairam Venugopal
On 1/10/17, 8:48 AM, "ovs-dev-boun...@openvswitch.org on behalf of Alin
Serdean"
Patch 2 and 3 could’ve been combined into the same patch since they are about
dst_port.
Acked-by: Sairam Venugopal
On 1/10/17, 8:48 AM, "ovs-dev-boun...@openvswitch.org on behalf of Alin
Serdean"
On 01/17/2017 05:43 PM, Ciara Loftus wrote:
> Instead of counting all polling cycles as processing cycles, only count
> the cycles where packets were received from the polling.
This makes these stats much clearer. One minor comment below, other than
that
Acked-by: Kevin Traynor
On Tue, Jan 17, 2017 at 01:45:02AM -0800, Mickey Spiegel wrote:
> This patch adds a description of logical routers and logical patch ports,
> including gateway routers, to ovn/ovn-architecture.7.xml.
>
> Signed-off-by: Mickey Spiegel
Thanks for working on the
" style="display:block; border:none; outline:none; text-decoration:none;
color:#ff !important; font-size:36px;"
Instead of counting all polling cycles as processing cycles, only count
the cycles where packets were received from the polling.
Signed-off-by: Georg Schmuecking
Signed-off-by: Ciara Loftus
Co-authored-by: Ciara Loftus
This issue happened on our in-use systems and we were trying to find a way
to move forward avoiding this issue so that we do not have to upgrade OVS
on thousands of our hypervisors causing down time. Our debugging did help
us avoid the issue for now by installing an explicit rule to to drop
It would be more helpful to have a simple reproduction case.
Why haven't you tried a newer version from branch-2.5?
On Tue, Jan 17, 2017 at 07:59:05AM -0800, Vidyasagara Guntaka wrote:
> Hi Ben,
>
> Here i is more debug information related to this incident (still using
> version 2.5.0):
>
>
Hi Ben,
Here i is more debug information related to this incident (still using version
2.5.0):
Summary :
We think that there is some race condition involved in processing OF Controller
connections and Packet miss processing in ovs-vswitchd.
Reasoning :
Please consider the following GDB
This patch implements the intermediate Tx queues on 'dpdk' type ports.
Test results:
* In worst case scenario with fewer packets per batch, a significant
bottleneck is observed for netdev_dpdk_eth_send() function due to
expensive MMIO writes.
* Also its observed that CPI(cycles per
After packet classification packets are queued in to batches depending
on the matching netdev flow. Thereafter each batch is processed to execute
the related actions. This becomes particularly inefficient if there
are few packets in each batch as rte_eth_tx_burst() incurs expensive MMIO
writes.
Self-NACK. Will include this change with another patch.
Antonio
> -Original Message-
> From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-
> boun...@openvswitch.org] On Behalf Of antonio.fische...@intel.com
> Sent: Wednesday, January 11, 2017 5:11 PM
> To: d...@openvswitch.org
>
Will respin a patch v2 where we addressed your comments.
So please let's continue our discussion on v2.
Thanks,
Antonio
> -Original Message-
> From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-
> boun...@openvswitch.org] On Behalf Of Fischetti, Antonio
> Sent: Thursday, January 12,
On Mon, Jan 16, 2017 at 5:14 PM, Ben Pfaff wrote:
> On Mon, Jan 16, 2017 at 04:46:58PM -0500, Russell Bryant wrote:
> > String a couple of closing HTML tags that were left over from when this
> doc
>
> s/String/Strip/
>
Oops, fixed.
>
> > was converted from the web site to RST.
On Sun, Jan 15, 2017 at 06:14:47PM +, Stokes, Ian wrote:
> > Since it's possible to delete memory pool in DPDK we can try to estimate
> > better required memory size when port is reconfigured, e.g. with different
> > number of rx queues.
>
> Thanks for the patch.
>
> It will need to be
This patch adds the new optional arguments "logical_port" and
"external_mac" to lr-nat-add, and displays that information in
lr-nat-list.
Signed-off-by: Mickey Spiegel
---
ovn/utilities/ovn-nbctl.8.xml | 27 +++---
ovn/utilities/ovn-nbctl.c | 54
Currently, for performance reasons on gateway routers, ct_snat
that does not specify an IP address does not immediately trigger
recirculation. On gateway routers, ct_snat that does not specify
an IP address happens in the UNSNAT pipeline stage, which is
followed by the DNAT pipeline stage that
This will make it easy for distributed NAT to reuse some of the
existing code for NAT flows, while leaving load balancing and defrag
as functionality specific to gateway routers. There is no intent to
change any functionality in this patch.
Signed-off-by: Mickey Spiegel
This patch adds an action that loops a clone of the packet back to the
beginning of the ingress pipeline with logical inport equal to the value
of the current logical outport. The following actions are executed on
the clone:
clears the connection tracking state
in_port = 0
inport =
Currently OVN distributed logical routers achieve reachability to
physical networks by passing through a "join" logical switch to a
centralized gateway router, which then connects to another logical
switch that has a localnet port connecting to the physical network.
This patch adds logical port
This patch introduces a new match expression component
is_chassis_resident(). Unlike match expression comparisons,
is_chassis_resident is not pushed down to OpenFlow. It is a
conditional that is evaluated in the controller during expr_simplify(),
when it is replaced by a boolean expression. The
This patch adds a description of logical routers and logical patch ports,
including gateway routers, to ovn/ovn-architecture.7.xml.
Signed-off-by: Mickey Spiegel
---
ovn/ovn-architecture.7.xml | 148 ++---
1 file changed, 140
On Mon, Jan 16, 2017 at 11:46 PM, Russell Bryant wrote:
>
>
> On Mon, Jan 16, 2017 at 12:01 PM, Ben Pfaff wrote:
>
>> On Mon, Jan 16, 2017 at 09:28:28AM -0500, Russell Bryant wrote:
>> > On Sat, Jan 14, 2017 at 11:29 AM, Ben Pfaff wrote:
>> >
>> > >
Currently OVS does not distinguish between a bond slave being operational
disabled, i.e. link being down, and administratively disabled.
Take the example where the administrator disabled a link in a bond,
"ovs-appctl bond/disable-slave bond0 enp129s0f0", it's automatically
enabled again due to
29 matches
Mail list logo