Re: [ovs-dev] [PATCH] datapath-windows: Account for VLAN tag in tunnel Decap

Alin, can we apply this patch? It’s been sitting around in the mailing list for a week without any reviews after an ACK. -- Thanks, Shashank On 11/21/17, 11:18 PM, "Anand Kumar" wrote: Acked-by: Anand Kumar Thanks, Anand Kumar

Re: [ovs-dev] [PATCH] openvswitch: use ktime_get_ts64() instead of ktime_get_ts()

On Mon, Nov 27, 2017 at 5:11 PM, Arnd Bergmann wrote: > timespec is deprecated because of the y2038 overflow, so let's convert > this one to ktime_get_ts64(). The code is already safe even on 32-bit > architectures, since it uses monotonic times. On 64-bit architectures, > nothing

Re: [ovs-dev] [PATCH 1/2] Update mailing list archive pointers to the current server.

> On Nov 27, 2017, at 2:57 PM, Ben Pfaff wrote: > > On Mon, Nov 27, 2017 at 02:28:37PM -0800, Justin Pettit wrote: >> Signed-off-by: Justin Pettit > > If you checked that the new URLs are correct (I did not), then: > Acked-by: Ben Pfaff Thanks.

Re: [ovs-dev] [PATCH 1/2] Update mailing list archive pointers to the current server.

On Mon, Nov 27, 2017 at 02:28:37PM -0800, Justin Pettit wrote: > Signed-off-by: Justin Pettit If you checked that the new URLs are correct (I did not), then: Acked-by: Ben Pfaff ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [PATCH 2/2] ovn/TODO: Remove some completed items.

On Mon, Nov 27, 2017 at 02:28:38PM -0800, Justin Pettit wrote: > Signed-off-by: Justin Pettit I think that these changes are correct. You might want to wait a day or so to see if anyone else speaks up. Acked-by: Ben Pfaff

Re: [ovs-dev] [PATCH] Revert "dpif_netdev: Refactor dp_netdev_pmd_thread structure."

On Mon, Nov 27, 2017 at 02:59:29PM +0300, Ilya Maximets wrote: > > I also verified the other case when posix_memalign isn't available and even > > in that case > > it returns the address aligned on CACHE_LINE_SIZE boundary. I will send out > > a patch to use > > xzalloc_cacheline for allocating

[ovs-dev] [PATCH 1/2] Update mailing list archive pointers to the current server.

Signed-off-by: Justin Pettit --- Documentation/internals/contributing/submitting-patches.rst | 2 +- Documentation/internals/security.rst| 2 +- lib/netdev-linux.c | 6 +++--- lib/ovs-thread.c

[ovs-dev] [PATCH] netdev-tc-offloads: Use customary types for buffer.

This function uses local array set_buff[] to store Netlink attributes. It declares set_buff as an array of character pointers, which is a strange type for a buffer of non-character-pointer objects. In OVS it is customary to use an ofpbuf with a stub of uint64_t objecs (to ensure proper alignment,

Re: [ovs-dev] OVS DPDK: dpdk_merge pull request

On Tue, Nov 21, 2017 at 01:14:53PM +, Stokes, Ian wrote: > > On Fri, Nov 17, 2017 at 07:27:51PM +, Stokes, Ian wrote: > > > The following changes since commit > > 1ae83bb20677b42d63dbb2140fa8ed3144c6260f: > > > > > > netdev-tc-offloads: Add support for action set (2017-11-16 08:10:29 > >

Re: [ovs-dev] Restore flows is slow using "ovs-save", is there someone who use RPC to speed up flow restore?

On Fri, Nov 24, 2017 at 11:07:07AM +0800, Sam wrote: > I'm working on speed up ovs restart, I found that restore flows is slow > when there are lots of flows, so I want to use RPC to store flows in > another process, and then restore from it. What RPC do you mean? Why do you think that your

[ovs-dev] Euro-Million Award Attached!

                             ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [CONNTRACK] Discussions at OvS 2017

Darrell, I think that you are working on some of the specific items that Aaron listed. Can you comment on that? On Sat, Nov 25, 2017 at 07:37:23PM +, Darrell Ball wrote: > Let me clarify some general points. > > 1/ We will not be porting any code from the Linux kernel, whether it be SIP >

Re: [ovs-dev] In ovs-2.4 version, why can't stop dpdk-bond port by `ovs-ofctl mod br dpdkbond DOWN`?

On Mon, Nov 27, 2017 at 06:07:35PM +0800, Sam wrote: > I'm working in ovs 2.4 version, and I use "dpdkb" type netdev. Then I > call `ovs-ofctl mod br dpdkbond DOWN` to down this device, at last, my > code call "rte_eth_dev_stop(dev->port_id);". > > But counter shows the port is still rx/tx, why?

Re: [ovs-dev] [PATCH] odp-util: Fix buffer overread in parsing string form of ODP flows.

On Sun, Nov 26, 2017 at 09:23:08PM -0800, Joe Stringer wrote: > On 26 November 2017 at 17:41, Ben Pfaff wrote: > > scan_u128() should return 0 on an error but it actually returned an errno > > value in some cases, so a command like this: > > ovs-appctl dpctl/add-flow

Re: [ovs-dev] [PATCH v2 0/2] OVN DB log fixes

OK, I did these backports. For branch-2.7 I had to backport all of the following commits to make these patches apply cleanly: commit 2abbe32153b7e4719b39f477b35e7cc40231338a Author: Numan Siddique Date: Wed Nov 8 14:28:49 2017 +0530 ovn-ctl: Add -vfile:info option to

Re: [ovs-dev] Failed to trace path into open flow groups

On Mon, Nov 27, 2017 at 04:24:47PM +0800, Yongsheng Gong wrote: > Hi, > > Ovs version 2.5.2: > Os: ubuntu 16.04 > > I have flows which in open flow groups, and I want to trace the path > of one kind of flow to know how it is got to a certain open flow port: I think that this is more of a bug in

[ovs-dev] Shrimp Top 15

If you are not able to see this mail, click http://r.newsletter.bonescamail.nl/7xa28kndqoatrf.html  Below you can find our special promotion on Vannamei and Black Tiger Shrimps   To get the price for 3 palets it is allowed to make a mix of all the varieties     * HOSO = Head On

Re: [ovs-dev] [PATCH] packets: Prefetch the packet metadata in cacheline1.

Hi Bhanu, Regards _Sugesh > -Original Message- > From: Bodireddy, Bhanuprakash > Sent: Monday, November 27, 2017 4:35 PM > To: 'Aaron Conole' > Cc: 'd...@openvswitch.org' ; Ben Pfaff ; > Chandran, Sugesh

Re: [ovs-dev] [PATCH] netdev-dpdk: Remove uneeded call to rte_eth_dev_count().

On 11/27/2017 04:19 PM, Loftus, Ciara wrote: >> >> The call to rte_eth_dev_count() was added as workaround >> for rte_eth_dev_get_port_by_name() not handling cases >> when there was no DPDK ports. In recent versions of DPDK, >> rte_eth_dev_get_port_by_name() does handle this >> case, so the

[ovs-dev] [PATCH v2] netdev-dpdk: Remove uneeded call to rte_eth_dev_count().

The call to rte_eth_dev_count() was added as workaround for rte_eth_dev_get_port_by_name() not handling cases when there was no DPDK ports. In versions of DPDK >= 17.02 rte_eth_dev_get_port_by_name() does handle this case (DPDK commit f9ae888b1e19). rte_eth_dev_count() is no longer needed so

[ovs-dev] [PATCH] odp-util: Avoid reading wrong table in generate_all_wildcard_mask().

These lines of code are intended to copy the 'next' and 'next_max' members of tbl[type] into local variables 'tbl' and 'max': tbl = tbl[type].next; max = tbl[type].next_max; They didn't do it properly because the first line changes 'tbl', so that the first and seconds

Re: [ovs-dev] [PATCH] Revert "dpif_netdev: Refactor dp_netdev_pmd_thread structure."

>I agree with Ilya here. Adding theses cache line markers and re-grouping >variables to minimize gaps in cache lines is creating a maintenance burden >without any tangible benefit. I have had to go through the pain of refactoring >my PMD Performance Metrics patch to the new dp_netdev_pmd_thread

Re: [ovs-dev] [dpdk-dev] [PATCH RFC] netdev-dpdk: Fix device obtain mac address when received first packet in vhost type

"Tan, Jianfeng" writes: > On 11/27/2017 10:27 PM, Yuanhan Liu wrote: >> On Fri, Nov 24, 2017 at 05:59:09PM +0800, Chen Hailin wrote: >>> Hi Aaron Conole && Jianfeng, >>> >>> The stp could not work in ovs-dpdk vhostuser. >>> Because the attached vhost device doesn't have

Re: [ovs-dev] [dpdk-dev] [PATCH RFC] netdev-dpdk: Fix device obtain mac address when received first packet in vhost type

On 11/28/2017 12:14 AM, Aaron Conole wrote: Yuanhan Liu writes: On Fri, Nov 24, 2017 at 05:59:09PM +0800, Chen Hailin wrote: Hi Aaron Conole && Jianfeng, The stp could not work in ovs-dpdk vhostuser. Because the attached vhost device doesn't have MAC address. Now we

Re: [ovs-dev] [PATCH] packets: Prefetch the packet metadata in cacheline1.

>>Bhanuprakash Bodireddy writes: >> >>> pkt_metadata_prefetch_init() is used to prefetch the packet metadata >>> before initializing the metadata in pkt_metadata_init(). This is done >>> for every packet in userspace datapath and is performance critical. >>> >>>

Re: [ovs-dev] [PATCH] netdev-dpdk: Remove uneeded call to rte_eth_dev_count().

> > The call to rte_eth_dev_count() was added as workaround > for rte_eth_dev_get_port_by_name() not handling cases > when there was no DPDK ports. In recent versions of DPDK, > rte_eth_dev_get_port_by_name() does handle this > case, so the rte_eth_dev_count() call can be removed. > > CC: Ciara

Re: [ovs-dev] [dpdk-dev] [PATCH RFC] netdev-dpdk: Fix device obtain mac address when received first packet in vhost type

Yuanhan Liu writes: > On Fri, Nov 24, 2017 at 05:59:09PM +0800, Chen Hailin wrote: >> Hi Aaron Conole && Jianfeng, >> >> The stp could not work in ovs-dpdk vhostuser. >> Because the attached vhost device doesn't have MAC address. >> >> Now we have two ways to solve this

Re: [ovs-dev] [dpdk-dev] [PATCH RFC] netdev-dpdk: Fix device obtain mac address when received first packet in vhost type

On 11/27/2017 10:27 PM, Yuanhan Liu wrote: On Fri, Nov 24, 2017 at 05:59:09PM +0800, Chen Hailin wrote: Hi Aaron Conole && Jianfeng, The stp could not work in ovs-dpdk vhostuser. Because the attached vhost device doesn't have MAC address. Now we have two ways to solve this problem. 1. The

[ovs-dev] [PATCH] netdev-dpdk: Remove uneeded call to rte_eth_dev_count().

The call to rte_eth_dev_count() was added as workaround for rte_eth_dev_get_port_by_name() not handling cases when there was no DPDK ports. In recent versions of DPDK, rte_eth_dev_get_port_by_name() does handle this case, so the rte_eth_dev_count() call can be removed. CC: Ciara Loftus

Re: [ovs-dev] [PATCH] Revert "dpif_netdev: Refactor dp_netdev_pmd_thread structure."

[ snip] >>> Yes, you will always get aligned addressess on your x86 Linux system >>> that supports >>> posix_memalign() call. The comment says what it says because it will >>> make some memory allocation tricks in case posix_memalign() is not >>> available (Windows, some MacOS, maybe some Linux

Re: [ovs-dev] [PATCH] ovs-ctl: Don't remember vport-* kernel modules

On Fri, Nov 10, 2017 at 02:45:05PM -0800, Gurucharan Shetty wrote: > From OVS 2.8, ovs-vswitchd, when it starts, will > load the kernel modules for tunnels. It has logic > inside it to choose either upstream kernel module > or vport-* kernel module. > > So, when we run 'force-reload-kmod' to

Re: [ovs-dev] [PATCH] net: openvswitch: datapath: fix data type in queue_gso_packets

Quoting David Miller : From: Willem de Bruijn Date: Sat, 25 Nov 2017 16:15:01 -0500 On Sat, Nov 25, 2017 at 2:14 PM, Gustavo A. R. Silva wrote: gso_type is being used in binary AND operations together with

Re: [ovs-dev] [PATCH v4 0/2] vHost Dequeue Zero Copy

Hi Ciara, > Thanks for your feedback. The limitation is only placed on phy port queues on > the VP (vhost -> phy) path. VV path and PV path are not > affected. Yes, you are right. VM to VM traffic is copied on transmit to the second VM. > > I would much rather put a requirement on tenants that

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

> > Conclusion: A global other_config parameter to enable/disable vhostuser > > IOMMU is sufficient. By default this could be OFF for now and changed > > to ON when broken Qemu versions are largely gone. > [Mooney, Sean K] hi yes I just responded to this before I saw your reply. > A global option

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

> -Original Message- > From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] > Sent: Monday, November 27, 2017 2:15 PM > To: Kavanagh, Mark B ; Mooney, Sean K > ; Kevin Traynor ; > d...@openvswitch.org > Cc:

Re: [ovs-dev] [dpdk-dev] [PATCH RFC] netdev-dpdk: Fix device obtain mac address when received first packet in vhost type

On Fri, Nov 24, 2017 at 05:59:09PM +0800, Chen Hailin wrote: > Hi Aaron Conole && Jianfeng, > > The stp could not work in ovs-dpdk vhostuser. > Because the attached vhost device doesn't have MAC address. > > Now we have two ways to solve this problem. > 1. The vhost learns MAC address from

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

> -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Monday, November 27, 2017 1:32 PM > To: Kavanagh, Mark B ; Mooney, Sean K > ; Jan Scheurich ; > d...@openvswitch.org > Cc:

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

>From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] >Sent: Monday, November 27, 2017 2:15 PM >To: Kavanagh, Mark B ; Mooney, Sean K >; Kevin Traynor ; >d...@openvswitch.org >Cc: maxime.coque...@redhat.com; Flavio Leitner

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

> >> >> Hi Mark, All, > >> >> > >> >> I'm thinking about this and whether the current approach provides > >> >> more than what is actually needed by users at the cost of making the > >> >> user interface more complex. > >[Mooney, Sean K] I am personally split on this. To enable iommu support in >

Re: [ovs-dev] [PATCH] tc: Fix build breakage on GCC 7 by annotating fall-through.

Acked-by: Paul Blakey On 27/11/2017 02:26, Ben Pfaff wrote: Open vSwitch enables the GCC 7+ option that warns about fall-through switch statements. This commit fixes newly introduced warnings. CC: Paul Blakey Fixes: d6118e628988 ("netdev-tc-offloads:

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

On 11/27/2017 12:55 PM, Kavanagh, Mark B wrote: > > >> From: Mooney, Sean K >> Sent: Sunday, November 26, 2017 11:28 PM >> To: Kavanagh, Mark B ; Jan Scheurich >> ; Kevin Traynor ; >> d...@openvswitch.org >> Cc:

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: add support for vhost IOMMU feature

>From: Mooney, Sean K >Sent: Sunday, November 26, 2017 11:28 PM >To: Kavanagh, Mark B ; Jan Scheurich >; Kevin Traynor ; >d...@openvswitch.org >Cc: maxime.coque...@redhat.com; Flavio Leitner ; Franck

Re: [ovs-dev] [PATCH] Revert "dpif_netdev: Refactor dp_netdev_pmd_thread structure."

On 24.11.2017 19:08, Bodireddy, Bhanuprakash wrote: >> On 22.11.2017 20:14, Bodireddy, Bhanuprakash wrote: This reverts commit a807c15796ddc43ba1ffb2a6b0bd2ad4e2b73941. Padding and aligning of dp_netdev_pmd_thread structure members is useless, broken in a several ways and only

[ovs-dev] [PATCH] openvswitch: use ktime_get_ts64() instead of ktime_get_ts()

timespec is deprecated because of the y2038 overflow, so let's convert this one to ktime_get_ts64(). The code is already safe even on 32-bit architectures, since it uses monotonic times. On 64-bit architectures, nothing changes, while on 32-bit architectures this avoids one type conversion.

Re: [ovs-dev] [PATCH] Revert "dpif_netdev: Refactor dp_netdev_pmd_thread structure."

I agree with Ilya here. Adding theses cache line markers and re-grouping variables to minimize gaps in cache lines is creating a maintenance burden without any tangible benefit. I have had to go through the pain of refactoring my PMD Performance Metrics patch to the new dp_netdev_pmd_thread

Re: [ovs-dev] In ovs-2.4 version, why can't stop dpdk-bond port by `ovs-ofctl mod br dpdkbond DOWN`?

The "dev->port_id" is bond port id, should I use slave port id instead ? 2017-11-27 18:07 GMT+08:00 Sam : > Hi all, > > I'm working in ovs 2.4 version, and I use "dpdkb" type netdev. Then I > call `ovs-ofctl mod br dpdkbond DOWN` to down this device, at last, my > code

[ovs-dev] In ovs-2.4 version, why can't stop dpdk-bond port by `ovs-ofctl mod br dpdkbond DOWN`?

Hi all, I'm working in ovs 2.4 version, and I use "dpdkb" type netdev. Then I call `ovs-ofctl mod br dpdkbond DOWN` to down this device, at last, my code call "rte_eth_dev_stop(dev->port_id);". But counter shows the port is still rx/tx, why? ___ dev

[ovs-dev] Failed to trace path into open flow groups

Hi, Ovs version 2.5.2: Os: ubuntu 16.04 I have flows which in open flow groups, and I want to trace the path of one kind of flow to know how it is got to a certain open flow port: Below is my actions in groups: gongysh@ubuntu16:~/routing$ sudo ovs-ofctl -O OpenFlow13 dump-groups s204