[ovs-dev] [PATCH v2] tunneling: Disable IPv6 tunnel

There are multiple issues in IPv6 userspace tunnel implementation. Even the kernel module that ships with 2.5 does not support IPv6 tunneling. There is not enough time to get all fixes in branch-2.5. So it make sense to disable the support on 2.5. Signed-off-by: Pravin B Shelar

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Add notes regarding vhost multiq configuration.

On 11.02.2016 23:02, Stokes, Ian wrote: >> Hi, Ian. >> I prepared a fix for this problem here: >> http://openvswitch.org/pipermail/dev/2016-February/066066.html >> >> Maybe it will be better than note in documentation. >> >> Best regards, Ilya Maximets. > > Thanks for the heads up on this Ilya,

[ovs-dev] [PATCH v4] ovn: Connect to remote lports through localnet port.

Before this patch, inter-chassis communication between VIFs of same lswitch will always go through tunnel, which end up of modeling a single physical network with many lswitches and pairs of lports, and complexity in CMS like OpenStack neutron to manage the lswitches and lports. With this patch,

[ovs-dev] Delivery reports about your e-mail

KcÍF%l׫F[敛À5^©SáIJ"½—{—áñp™Úâ„ñ»)bªNj7*¤íÀ$ÍÉCIÔ ¶q\}µèC2VzBî£mÕ0)lÈX1… ïY*÷–¦Ñ]'q-¶I¾ª‰WíÑ­¬—ßûÈÇpñÅÕ`ᬒì6ѐCE'V‚ãSìªb-èA¯ø¨v±$ÝÇ ÷¡ Ç6Y"TäÞX}¨¾á2FgêÐbgµNŽöPGLßNv ___ dev mailing list dev@openvswitch.org

[ovs-dev] [PATCH RFC v2] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

Currently virtio driver in guest operating system have to be configured to use exactly same number of queues. If number of queues will be less, some packets will get stuck in queues unused by guest and will not be received. Fix that by using new 'vring_state_changed' callback, which is available

Re: [ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

On 11.02.2016 20:31, Aaron Conole wrote: > Hi Ilya, > > Ilya Maximets writes: > >> Currently virtio driver in guest operating system have to be configured >> to use exactly same number of queues. If number of queues will be less, >> some packets will get stuck in queues

Re: [ovs-dev] [PATCH v3] ovn-controller: Assign zone-id consistently

> On Feb 11, 2016, at 5:18 PM, Ramu Ramamurthy > wrote: > > @@ -65,6 +66,8 @@ get_local_iface_ids(const struct ovsrec_bridge *br_int, > struct shash *lports) > > for (j = 0; j < port_rec->n_interfaces; j++) { > const struct ovsrec_interface

Re: [ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

On 12.02.2016 09:00, Ilya Maximets wrote: > Hi, Flavio. > > Comment inlined. > > On 12.02.2016 07:44, Flavio Leitner wrote: >> >> Hi Ilya, >> >> On Thu, 11 Feb 2016 16:04:12 +0300 >> Ilya Maximets wrote: >> >>> Currently virtio driver in guest operating system have to

Re: [ovs-dev] [PATCH v3] ovn-controller: Assign zone-id consistently

> On Feb 11, 2016, at 5:18 PM, Ramu Ramamurthy > wrote: I'll let Russell do the full review, but I had one other small suggestion from looking at the code: > @@ -72,13 +75,65 @@ get_local_iface_ids(const struct ovsrec_bridge *br_int, > struct shash *lports) >

Re: [ovs-dev] [PATCH v3] netdev_dpdk.c: Add QoS functionality.

> On Thu, 11 Feb 2016 12:32:56 + > "Stokes, Ian" wrote: > > > Thanks For the review Flavio, much appreciated, comments inline. I'll > re-spin a new version also. > > Thank you for the patch! > comments inline. > > > > > > > -Original Message- > > > From:

Re: [ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

Hi, Flavio. Comment inlined. On 12.02.2016 07:44, Flavio Leitner wrote: > > Hi Ilya, > > On Thu, 11 Feb 2016 16:04:12 +0300 > Ilya Maximets wrote: > >> Currently virtio driver in guest operating system have to be configured >> to use exactly same number of queues. If

Re: [ovs-dev] [PATCH v4] ofpbuf: Make ofpbuf_put_hex() accept period between hex bytes also.

Acked-by: Jarno Rajahalme > On Feb 10, 2016, at 3:56 PM, Ben Pfaff wrote: > > This makes it accept the same syntax as parse_NOTE(), so that that function > can be simplified. In an upcoming commit a second action will also be > able to take advantage of the same

Re: [ovs-dev] [PATCH v3 7/7] Implement "closures".

With the (few) comments below: Acked-by: Jarno Rajahalme (snip) > + * In the current implementation, Open vSwitch forks the packet processing > + * pipeline across patch ports. Suppose, for example, that the pipeline for > + * br0 outputs to a patch port whose peer belongs to

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Add notes regarding vhost multiq configuration.

> Hi, Ian. > I prepared a fix for this problem here: > http://openvswitch.org/pipermail/dev/2016-February/066066.html > > Maybe it will be better than note in documentation. > > Best regards, Ilya Maximets. Thanks for the heads up on this Ilya, am I right in thinking this removes the need to

[ovs-dev] [PATCH v9 5/6] netdev-dpdk: Check dpdk-extra when reading db

A previous patch introduced the ability to pass arbitrary EAL command line options via the dpdk_extras database entry. This commit enhances that by warning the user when such a configuration is detected and prefering the value in the database. Suggested-by: Sean K Mooney

[ovs-dev] [PATCH v9 3/6] netdev-dpdk: Autofill lcore coremask if absent

The user has control over the DPDK internal lcore coremask, but this parameter can be autofilled with a bit more intelligence. If the user does not fill this parameter in, we use the lowest set bit in the current task CPU affinity. Otherwise, we will reassign the current thread to the specified

[ovs-dev] [PATCH v9 2/6] netdev-dpdk: Convert initialization from cmdline to db

Existing DPDK integration is provided by use of command line options which must be split out and passed to librte in a special manner. However, this forces any configuration to be passed by way of a special DPDK flag, and interferes with ovs+dpdk packaging solutions. This commit delays dpdk

[ovs-dev] [PATCH v9 2/6] netdev-dpdk: Convert initialization from cmdline to db

Existing DPDK integration is provided by use of command line options which must be split out and passed to librte in a special manner. However, this forces any configuration to be passed by way of a special DPDK flag, and interferes with ovs+dpdk packaging solutions. This commit delays dpdk

[ovs-dev] [PATCH v9 1/6] netdev-dpdk: Restore thread affinity after DPDK init

When the DPDK init function is called, it changes the executing thread's CPU affinity to a single core specified in -c. This will result in the userspace bridge configuration thread being rebound, even if that is not the intent. This change fixes that behavior by rebinding to the original thread

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

Joe, I just noticed I never sent this out. Sorry, and thanks for the review! Jarno > On Feb 3, 2016, at 2:19 PM, Joe Stringer wrote: > > On 3 February 2016 at 12:33, Jarno Rajahalme wrote: >> From: Ethan Jackson >> >> There are certain use

[ovs-dev] [PATCH v9 1/6] netdev-dpdk: Restore thread affinity after DPDK init

When the DPDK init function is called, it changes the executing thread's CPU affinity to a single core specified in -c. This will result in the userspace bridge configuration thread being rebound, even if that is not the intent. This change fixes that behavior by rebinding to the original thread

[ovs-dev] [PATCH v9 0/6] Convert DPDK configuration from command line to DB based

Currently, configuration of DPDK parameters is done via the command line through a --dpdk **OPTIONS** -- command line argument. This has a number of challenges, including: * It must be the first option passed to ovs-vswitchd * It is the only datapath feature in OVS to be configured on the command

[ovs-dev] [PATCH v9 4/6] netdev-dpdk: Allow arbitrary eal arguments

A previous change moved some commonly used arguments from commandline to the database, and with it the ability to pass arbitrary arguments to EAL. This change allows arbitrary eal arguments to be provided via a new db entry 'other_config:dpdk-extra' which will tokenize the string and add it to the

[ovs-dev] [PATCH v9 0/6] Convert DPDK configuration from command line to DB based

Currently, configuration of DPDK parameters is done via the command line through a --dpdk **OPTIONS** -- command line argument. This has a number of challenges, including: * It must be the first option passed to ovs-vswitchd * It is the only datapath feature in OVS to be configured on the command

Re: [ovs-dev] [OVS-dev]: OVN: RFC re: logical and physical endpoint separation proposal

On 02/10/2016 09:56 PM, Darrell Ball wrote: > Hi Russell > > Please see inline > > Thanks Darrell > > > > On 2/8/16, 12:38 PM, "Russell Bryant" wrote: > >> On 02/08/2016 12:05 PM, Darrell Ball wrote: >>> On 2/5/16, 12:23 PM, "Russell Bryant" wrote: I

[ovs-dev] [PATCH v9 6/6] NEWS: Announce the DPDK EAL configuration change

Previous commits have converted dpdk EAL initialization from requiring a ``--dpdk ... --`` command line arguments to using the Open vSwitch database. This change announces that as significant NEWS. Signed-off-by: Aaron Conole Tested-by: RobertX Wojciechowicz

Re: [ovs-dev] [PATCH 2/2] expr: Fix memory leak reported by valgrind.

On 02/11/2016 12:45 PM, William Tu wrote: > Testcase 1728: ovn -- 5-term mixed expression normalization. > expr_clone_cmp (expr.c:1259) > expr_clone (expr.c:1284) > expr_clone_andor (expr.c:1271) > expr_clone (expr.c:1288) > expr_normalize_and (expr.c:2137) >

Re: [ovs-dev] [PATCH v3] netdev_dpdk.c: Add QoS functionality.

Thanks For the review Flavio, much appreciated, comments inline. I'll re-spin a new version also. > -Original Message- > From: Flavio Leitner [mailto:f...@sysclose.org] > Sent: Wednesday, February 10, 2016 7:55 PM > To: Stokes, Ian > Cc: dev@openvswitch.org > Subject: Re: [ovs-dev]

[ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

Currently virtio driver in guest operating system have to be configured to use exactly same number of queues. If number of queues will be less, some packets will get stuck in queues unused by guest and will not be received. Fix that by using new 'vring_state_changed' callback, which is available

Re: [ovs-dev] [PATCH V3] netdev-dpdk: Add Jumbo Frame Support.

> > >On 08/02/2016 03:23, "Kavanagh, Mark B" wrote: > >>> >>>Hi Mark, >>> >> >>Hi Daniele, >> >>Thanks for the review! Responses inline below. >> >>Cheers, >>Mark >> >>>This patch besides adding Jumbo Frame support also cleans up >>>the mbuf initialization (by changing

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Add notes regarding vhost multiq configuration.

Hi, Ian. I prepared a fix for this problem here: http://openvswitch.org/pipermail/dev/2016-February/066066.html Maybe it will be better than note in documentation. Best regards, Ilya Maximets. On 09.02.2016 17:40, Ian Stokes wrote: > Linux kernel network devices in a guest should have the

Re: [ovs-dev] [PATCH v3] netdev_dpdk.c: Add QoS functionality.

Thanks for the review Daniele, comments inline. Will re-spin another version. > Thanks for the patch and the review. > > I agree with everything Flavio pointed out, a few more comments below > > On 10/02/2016 11:54, "Flavio Leitner" wrote: > > >On Mon, 1 Feb 2016 20:47:25

Re: [ovs-dev] [PATCH v3] netdev_dpdk.c: Add QoS functionality.

On Thu, 11 Feb 2016 12:32:56 + "Stokes, Ian" wrote: > Thanks For the review Flavio, much appreciated, comments inline. I'll re-spin > a new version also. Thank you for the patch! comments inline. > > > -Original Message- > > From: Flavio Leitner

[ovs-dev] [PATCH] ofproto-dpif : propagate may_enable flag as link aliveness

Hi, The idea is to use OFPPS_LIVE bit to propagate link aliveness state towards the controller also when sending port status. The ofport->may_enable flag could be used for this purpose. I updated some unit tests according to the changes of ofproto-dpif. Signed-off-by: Zoltán Balogh

Re: [ovs-dev] [PATCH v1] Basic GTP-U tunnel implementation in ovs

On 5 February 2016 at 10:50, Ben Pfaff wrote: > On Fri, Feb 05, 2016 at 04:17:43PM +0530, Niti Rohilla wrote: >> GPRS Tunneling Protocol (GTP) is a group of IP-based communications protocols >> used to carry general packet radio service (GPRS) within GSM, UMTS >> and LTE networks.

[ovs-dev] OVN implementation of the NAT/FIP architecture

Hi, I see interest in OVN implementing the conventional NAT/FIP architecture from the OpenStack Networking service (neutron) and think it warrants further discussion to make sure the project takes an optimal approach to it. For those not familiar with neutron, routers between provider and

Re: [ovs-dev] [PATCH] Installation steps correction for DPDK 2.2.

On Fri, 5 Feb 2016 11:42:06 + mweglicx wrote: > Missing step added to INSTALL.DPDK.md which prevents > installation error message. > > Signed-off-by: Michal Weglicki > --- > INSTALL.DPDK.md | 20 ++-- > 1 file

[ovs-dev] [PATCH v3] ovn-controller: Assign zone-id consistently

Currently, ovn-controller does not record the lport->zoneid map, and so, after ovn-controller restart, zone-ids may get set inconsistently on lports, resulting in possible hits to already established connections. Set zone-id as an external-id of the interface record, and recover the zone-id from

Re: [ovs-dev] [ovs-dev, v3] ovn: Connect to remote lports through localnet port.

On 02/05/2016 05:53 PM, Han Zhou wrote: > Before this patch, inter-chassis communication between VIFs of same > lswitch will always go through tunnel, which end up of modeling a > single physical network with many lswitches and pairs of lports, and > complexity in CMS like OpenStack neutron to

[ovs-dev] [PATCH v2 3/5] datapath-windows: Support for OVS_ACTION_ATTR_HASH attribute

Signed-off-by: Sorin Vinturis --- datapath-windows/ovsext/Actions.c| 32 datapath-windows/ovsext/DpInternal.h | 1 + datapath-windows/ovsext/Flow.c | 13 + 3 files changed, 46 insertions(+) diff --git

[ovs-dev] [PATCH v2 5/5] datapath-windows: Updated FAQ regarding Hyper-V recirculation.

Updated FAQ document to reflect recirculation support for Hyper-V. Signed-off-by: Sorin Vinturis --- FAQ.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/FAQ.md b/FAQ.md index 8bd7ab9..062f164 100644 --- a/FAQ.md +++ b/FAQ.md @@ -226,7

Re: [ovs-dev] [OVS-dev]: OVN: RFC re: logical and physical endpoint separation proposal

On 2/11/16, 12:20 PM, "Russell Bryant" wrote: >On 02/10/2016 09:56 PM, Darrell Ball wrote: >> Hi Russell >> >> Please see inline >> >> Thanks Darrell >> >> >> >> On 2/8/16, 12:38 PM, "Russell Bryant" wrote: >> >>> On 02/08/2016 12:05 PM, Darrell Ball

[ovs-dev] [PATCH v2 1/5] datapath-windows: Added recirculation support.

Recirculation support for the OVS extension. Tested with PING using MPLS packets. Signed-off-by: Sorin Vinturis Co-authored-by: Alin Gabriel Serdean Reported-by: Sorin Vinturis Reported-at:

[ovs-dev] [PATCH v2 0/5] datapath-windows: Recirculation support

This patch series adds support for recirculation to the OVS extension. Sorin Vinturis (5): [PATCH v2 1/5] datapath-windows: Added recirculation support. [PATCH v2 2/5] datapath-windows: Allow recirculation feature probe. [PATCH v2 3/5] datapath-windows: Support for OVS_ACTION_ATTR_HASH attr

[ovs-dev] [PATCH v2 2/5] datapath-windows: Allow recirculation feature probe.

Recirculation feature probe messages sent from userspace are suppressed by the OVS extension. This patch changes the current behaviour to allow feature probe for recirculation. Signed-off-by: Sorin Vinturis --- datapath-windows/ovsext/Flow.c | 9 - 1

[ovs-dev] [PATCH v2 4/5] datapath-windows: Extract flow metadata in execute cmd handler.

Signed-off-by: Sorin Vinturis --- datapath-windows/ovsext/DpInternal.h | 1 + datapath-windows/ovsext/Flow.c | 17 + datapath-windows/ovsext/Flow.h | 2 ++ datapath-windows/ovsext/User.c | 7 +++ 4 files changed, 27

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Update details of XL710 restrictions for DPDK 2.2.

On Tue, 9 Feb 2016 14:48:47 + Ian Stokes wrote: > DPDK 2.2 removes restrictions related to maximum number of TX > queues for XL710 devices. Update documentation to reflect these > changes. > > Signed-off-by: Ian Stokes > --- > INSTALL.DPDK.md |

Re: [ovs-dev] [PATCH v2] : ovn-controller - Assign zone-ids consistently

> On Feb 10, 2016, at 12:14 PM, Russell Bryant wrote: > >> @@ -112,10 +171,8 @@ update_ct_zones(struct sset *lports, struct simap >> *ct_zones, >> bitmap_set1(ct_zone_bitmap, zone); >> simap_put(ct_zones, iface_id, zone); >> >> -/* xxx We should erase

Re: [ovs-dev] [PATCH v2] tunneling: Disable IPv6 tunnel

On Thu, 11 Feb 2016 01:05:16 -0800 Pravin B Shelar wrote: > There are multiple issues in IPv6 userspace tunnel > implementation. Even the kernel module that ships with > 2.5 does not support IPv6 tunneling. There is not > enough time to get all fixes in branch-2.5. So it make >

Re: [ovs-dev] [ovs-dev, v3] ovn: Connect to remote lports through localnet port.

On Thu, Feb 11, 2016 at 12:58 PM, Russell Bryant wrote: > > On 02/05/2016 05:53 PM, Han Zhou wrote: > > Before this patch, inter-chassis communication between VIFs of same > > lswitch will always go through tunnel, which end up of modeling a > > single physical network with many

Re: [ovs-dev] [PATCH] INSTALL.DPDK.md: Correct mergeable buffers parameter.

On Wed, 10 Feb 2016 10:50:54 + Ian Stokes wrote: > Update the mergeable buffers paramaters in performance tuning > to the correct parameter mrg_rxbuf. > > Signed-off-by: Ian Stokes > --- > INSTALL.DPDK.md |2 +- > 1 files changed, 1

Re: [ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

Hi Ilya, On Thu, 11 Feb 2016 16:04:12 +0300 Ilya Maximets wrote: > Currently virtio driver in guest operating system have to be configured > to use exactly same number of queues. If number of queues will be less, > some packets will get stuck in queues unused by guest

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Add notes regarding vhost multiq configuration.

On Tue, 9 Feb 2016 14:40:53 + Ian Stokes wrote: > Linux kernel network devices in a guest should have the number of > multi-purpose channels configured when used with DPDK multiqueue on the host. > This commit adds an example of how this can be done. Also add QEMU 2.5

Re: [ovs-dev] [PATCH v2] dpif-netdev: Add dpif-netdev/pmd-rxq-show appctl command.

On Mon, 08 Feb 2016 10:38:47 +0300 Ilya Maximets wrote: > This command can be used to check the port/rxq assignment to > pmd threads. For each pmd thread of the datapath shows list > of queue-ids with port names. > > Additionally log message from pmd_thread_main()

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

Daniele Di Proietto writes: > On 09/02/2016 09:48, "Traynor, Kevin" wrote: > >> >> >>> -Original Message- >>> From: Aaron Conole [mailto:acon...@redhat.com] >>> Sent: Friday, January 29, 2016 5:57 PM >>> To: dev@openvswitch.org >>> Cc:

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

Hi Sean, "Mooney, Sean K" writes: > Overall I like this change but as a user of ovs with dpdk and > A maintainer of a plugin to deploy it I have some comments inline. AWESOME! Seriously, I will probably be bothering you a lot because you are the person I want to hear

Re: [ovs-dev] [PATCH RFC] netdev-dpdk: vhost-user: Fix sending packets to queues not enabled by guest.

Hi Ilya, Ilya Maximets writes: > Currently virtio driver in guest operating system have to be configured > to use exactly same number of queues. If number of queues will be less, > some packets will get stuck in queues unused by guest and will not be > received. > > Fix

[ovs-dev] [PATCH 1/2] expr: Fix memory leak reported by valgrind.

Testcase 1728: ovn -- 5-term mixed expression normalization Call stack: sset_add__ (sset.c:53) crush_and_string (expr.c:1725) crush_cmps (expr.c:1998) expr_sort (expr.c:2050) expr_normalize_and (expr.c:2085) Signed-off-by: William Tu Signed-off-by: Daniele

[ovs-dev] [PATCH 2/2] expr: Fix memory leak reported by valgrind.

Testcase 1728: ovn -- 5-term mixed expression normalization. expr_clone_cmp (expr.c:1259) expr_clone (expr.c:1284) expr_clone_andor (expr.c:1271) expr_clone (expr.c:1288) expr_normalize_and (expr.c:2137) test_tree_shape_exhaustively (test-ovn.c:926) Signed-off-by: William