[ovs-dev] [per-pmd ftb/cls 3/3] dpif-netdev: Add per-pmd flow-table/classifier.

This commit changes the per dpif-netdev datapath flow-table/ classifier to per pmd-thread. As direct benefit, datapath and flow statistics no longer need to be protected by mutex or be declared as per-thread variable, since they are only written by the owning pmd thread. As side effects, the flow

[ovs-dev] [per-pmd ftb/cls 2/3] ovs-numa: Allow user query the pinned cores on a numa node.

This commit adds function in ovs-numa module which allows users to query the pinned cores on a numa node by providing the numa node id and a pre-allocated bitmap. The ovs-numa module will set the bit in bitmap for each pinned core. Signed-off-by: Alex Wang --- lib/ovs-numa.c | 23

[ovs-dev] [per-pmd ftb/cls 1/3] dpif-netdev: Add function to get pmd using core id.

This commit adds the function dp_netdev_get_pmd() which allows users to get 'struct dp_netdev_pmd_thread' based on the core id. Signed-off-by: Alex Wang --- lib/dpif-netdev.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.

Re: [ovs-dev] OFPFMFC_OVERLAP Error

Hi Ben Could you please let me know if this feature implementation is supported in OVS or not. Also, I am new to this and do not know how I can find status of EXT-406. Meanwhile I found this below link online which gives a way to implement this flag it is by changing fm->flags=2; in ofp-parse.c

[ovs-dev] [Discussion] About over-MTU-sized skb in virtualized env

Sorry for resend this mail, because my company email is rejected by netdev. Hi Florian 214 static int ip_finish_output_gso(struct sk_buff *skb) 215 { 216 netdev_features_t features; 217 struct sk_buff *segs; 218 int ret = 0; 219 220 /* common case: locally created skb or

Re: [ovs-dev] [PATCH] datapath-windows: Add PID Number attribute for port notification / Fix logic

Acked-by: Sorin Vinturis -Original Message- From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma Sent: Wednesday, 3 December, 2014 02:23 To: Eitan Eliahu; dev@openvswitch.org Subject: Re: [ovs-dev] [PATCH] datapath-windows: Add PID Number attribute for port notificati

[ovs-dev] [Discussion] About over-MTU-sized skb in virtualized env

Hi Florian 214 static int ip_finish_output_gso(struct sk_buff *skb) 215 { 216 netdev_features_t features; 217 struct sk_buff *segs; 218 int ret = 0; 219 220 /* common case: locally created skb or seglen is <= mtu */ 221 if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||

[ovs-dev] [PATCHv11 net-next 1/2] openvswitch: Refactor ovs_nla_fill_match().

Refactor the ovs_nla_fill_match() function into separate netlink serialization functions ovs_nla_put_{unmasked_key,masked_key,mask}(). Modify ovs_nla_put_flow() to handle attribute nesting and expose the 'is_mask' parameter - all callers need to nest the flow, and callers have better knowledge abou

[ovs-dev] [PATCHv11 net-next 2/2] openvswitch: Add support for unique flow IDs.

Previously, flows were manipulated by userspace specifying a full, unmasked flow key. This adds significant burden onto flow serialization/deserialization, particularly when dumping flows. This patch adds an alternative way to refer to flows using a variable-length "unique flow identifier" (UFID).

Re: [ovs-dev] [ovs-build] Broken: openvswitch/ovs#458 (master - 64bb477)

This seems to be some race condition that sometimes occurs now that ukey entries are created in handler threads. I've got a solution in mind, but I'd like to run an overnight test to check that it works reliably. On 2 December 2014 at 15:34, Travis CI wrote: >*openvswitch / ovs >

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

>-Original Message- >From: Thomas Graf [mailto:t...@infradead.org] On Behalf Of Thomas Graf >Sent: Wednesday, December 3, 2014 1:42 AM >To: Michael S. Tsirkin >Cc: Du, Fan; 'Jason Wang'; net...@vger.kernel.org; da...@davemloft.net; >f...@strlen.de; dev@openvswitch.org; je...@nicira.com; p

Re: [ovs-dev] Understanding different ovs components

Thanks Ben. Mehul.  On Wednesday, December 3, 2014 1:07 AM, Ben Pfaff wrote: On Tue, Dec 02, 2014 at 10:42:09AM +, Mehul Vora wrote: > ??I am trying to understand different components of ovs. Please correct me if > my understanding is wrong,?? > 1. ovsdb-server : Maintains openv

Re: [ovs-dev] [PATCH] datapath-windows: Add PID Number attribute for port notification / Fix logic

Acked-by: Ankur Sharma From: dev on behalf of Eitan Eliahu Sent: Tuesday, December 2, 2014 8:33 PM To: dev@openvswitch.org Subject: [ovs-dev] [PATCH] datapath-windows: Add PID Number attribute for port notification / Fix logic [1] User mode OVS e

[ovs-dev] Bug#771863: openvswitch-switch: Open vSwitch configuration through /etc/network/interfaces does not work

Package: openvswitch-switch Version: 2.3.0+git20140819-2 Severity: normal Tags: patch Dear Maintainer, i used one of the simple example configurations from the file README.Debian.gz to configure an Open vSwitch in /etc/network/interfaces. allow-ovs br0 iface br0 inet dhcp ovs_type OVSBr

Re: [ovs-dev] [PATCHv11 1/5] datapath: Add UFID interface to openvswitch.h.

Thanks for review, I pushed patches #1-3 to master. I plan to send the datapath changes to net-next this afternoon. On 2 December 2014 at 13:48, Pravin Shelar wrote: > On Tue, Nov 25, 2014 at 5:07 PM, Joe Stringer wrote: >> An upcoming set of patches will implement support for indexing flows by

Re: [ovs-dev] [PATCHv11 1/5] datapath: Add UFID interface to openvswitch.h.

On Tue, Nov 25, 2014 at 5:07 PM, Joe Stringer wrote: > An upcoming set of patches will implement support for indexing flows by > Unique Flow IDentifiers (UFID) rather than the traditional unmasked key. > This patch implements the interface changes required. The implementation > will follow. > > Si

Re: [ovs-dev] [PATCH] classifier: Silence sparse warning (sparse bug)

On Fri, Nov 28, 2014 at 01:45:16PM +0100, Thomas Graf wrote: > This silences the following sparse warning which appears to be a bug > in sparse: > > lib/classifier-private.h:210:45: warning: call with no type! > lib/classifier-private.h:179:45: warning: call with no type! > > Can be r

[ovs-dev] [PATCH] datapath-windows: Add PID Number attribute for port notification / Fix logic

[1] User mode OVS expects to have the PID number in the port state notification command [2] Fix logic error-for-Windows-user-mode Signed-off-by: Eitan Eliahu --- datapath-windows/ovsext/Datapath.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/datapath-win

Re: [ovs-dev] [PATCH] dpif: Don't clear argument in dp_enumerate_types().

On Tue, Dec 02, 2014 at 10:55:16AM -0800, Ben Pfaff wrote: > All but one of the callers of dp_enumerate_types() hands it an sset that is > known to be empty. The one exception is the implementation of the > ofproto-provider 'enumerate_types' function in ofproto-dpif. That function > isn't suppose

[ovs-dev] Bug#771507: openvswitch-switch: missing systemd files

You're correct 2.3.90-1 is not in debian as the .debs used were built from source, but if I recall systemd files are also missing from 2.3.0+git20140819-2 On 02/12/14 02:18 PM, Ben Pfaff wrote: On Sun, Nov 30, 2014 at 05:53:17AM -0500, westlake wrote: Package: openvswitch-switch Version: 2.3

Re: [ovs-dev] Understanding different ovs components

On Tue, Dec 02, 2014 at 10:42:09AM +, Mehul Vora wrote: > ??I am trying to understand different components of ovs. Please correct me if > my understanding is wrong,?? > 1. ovsdb-server : Maintains openvswtich configuration databse.?? > 2. ovs-vswitchd : Dameon that controls all Open vSwitch sw

Re: [ovs-dev] OFPFMFC_OVERLAP Error

On Tue, Dec 02, 2014 at 11:30:26AM -0800, Ben Pfaff wrote: > On Mon, Dec 01, 2014 at 10:50:45PM -0800, varanasi sandhya wrote: > > OFPFF_CHECK_OVERLAP flag Issue: > > > > When OFPFF_CHECK_OVERLAP flag is set at RYU controller in ofctl_v1_3.py > > code in the mod_flow_entry definition, OVS should i

Re: [ovs-dev] OFPFMFC_OVERLAP Error

On Mon, Dec 01, 2014 at 10:50:45PM -0800, varanasi sandhya wrote: > OFPFF_CHECK_OVERLAP flag Issue: > > When OFPFF_CHECK_OVERLAP flag is set at RYU controller in ofctl_v1_3.py > code in the mod_flow_entry definition, OVS should ideally return > OFPFMFC_OVERLAP error on inserting a duplicate flow w

[ovs-dev] Bug#771507: openvswitch-switch: missing systemd files

On Sun, Nov 30, 2014 at 05:53:17AM -0500, westlake wrote: > Package: openvswitch-switch > Version: 2.3.90-1 > Severity: important > > openvswitch is missing systemd files in order for other network > services to work. > > over here ssh would not bind to an address unless ovs has been > started pr

Re: [ovs-dev] adding new ofproto provider

Thanks, I applied the patch to master. On Tue, Dec 02, 2014 at 07:25:41PM +, Zolt?n Balogh wrote: > Hi Ben, > > It's ok. I also applied the patch and run 'make check'. All tests passed. > > Regards, > Zoltan > > -Original Message- > From: Zolt?n Balogh > Sent: Tuesday, December 02,

Re: [ovs-dev] adding new ofproto provider

Hi Ben, It's ok. I also applied the patch and run 'make check'. All tests passed. Regards, Zoltan -Original Message- From: Zoltán Balogh Sent: Tuesday, December 02, 2014 8:01 PM To: 'Ben Pfaff' Cc: dev@openvswitch.org Subject: RE: [ovs-dev] adding new ofproto provider Hi Ben, Yes, I w

Re: [ovs-dev] [PATCH] NEWS: Multicast snooping was introduced after, not before, version 2.3.

On Wed, Nov 26, 2014 at 07:06:05PM -0200, Flavio Leitner wrote: > On Thu, Nov 20, 2014 at 08:38:15AM -0800, Ben Pfaff wrote: > > Reported-by: Helmut Schaa > > Signed-off-by: Ben Pfaff > > --- > > Acked-by: Flavio Leitner > > Thanks Ben! > fbl Thanks, applied to master. ___

Re: [ovs-dev] [PATCH 2/3] docs: Add titles to documentation files that lacked them.

On Thu, Nov 27, 2014 at 11:35:30PM +0100, Thomas Graf wrote: > Missing S-O-B ;-) Thanks for noticing. Added. > Acked-by: Thomas Graf Thanks for all the reviews. I applied these to master. ___ dev mailing list dev@openvswitch.org http://openvswitch.o

Re: [ovs-dev] adding new ofproto provider

Hi Ben, Yes, I will review it. Regards, Zoltan -Original Message- From: Ben Pfaff [mailto:b...@nicira.com] Sent: Tuesday, December 02, 2014 7:56 PM To: Zoltán Balogh Cc: dev@openvswitch.org Subject: Re: [ovs-dev] adding new ofproto provider On Tue, Dec 02, 2014 at 01:41:10PM +, Zol

Re: [ovs-dev] adding new ofproto provider

On Tue, Dec 02, 2014 at 01:41:10PM +, Zolt?n Balogh wrote: > Dear Sirs, > > I'm working on a project in which the goal is to add a new ofproto provider > to ovs while keeping ofproto_dpif. We use ovs version I created a new > ofproto _class (ofproto_new) and I register an instance of this

[ovs-dev] [PATCH] dpif: Don't clear argument in dp_enumerate_types().

All but one of the callers of dp_enumerate_types() hands it an sset that is known to be empty. The one exception is the implementation of the ofproto-provider 'enumerate_types' function in ofproto-dpif. That function isn't supposed to clear the existing contents of the sset passed in. Therefore,

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

On Tue, Dec 2, 2014 at 9:41 AM, Thomas Graf wrote: > On 12/02/14 at 07:34pm, Michael S. Tsirkin wrote: >> On Tue, Dec 02, 2014 at 05:09:27PM +, Thomas Graf wrote: >> > On 12/02/14 at 01:48pm, Flavio Leitner wrote: >> > > What about containers or any other virtualization environment that >> > >

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

On 12/02/14 at 07:34pm, Michael S. Tsirkin wrote: > On Tue, Dec 02, 2014 at 05:09:27PM +, Thomas Graf wrote: > > On 12/02/14 at 01:48pm, Flavio Leitner wrote: > > > What about containers or any other virtualization environment that > > > doesn't use Virtio? > > > > The host can dictate the MTU

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

On Tue, Dec 02, 2014 at 05:09:27PM +, Thomas Graf wrote: > On 12/02/14 at 01:48pm, Flavio Leitner wrote: > > What about containers or any other virtualization environment that > > doesn't use Virtio? > > The host can dictate the MTU in that case for both veth or OVS > internal which would be p

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

On 12/02/14 at 01:48pm, Flavio Leitner wrote: > What about containers or any other virtualization environment that > doesn't use Virtio? The host can dictate the MTU in that case for both veth or OVS internal which would be primary container plumbing techniques. ivshmem would need it's own fix. _

Re: [ovs-dev] [PATCH net] gso: do GSO for local skb with size bigger than MTU

On Mon, Dec 01, 2014 at 01:52:25PM +, Thomas Graf wrote: > On 11/30/14 at 10:08am, Du, Fan wrote: > > >-Original Message- > > >From: Jason Wang [mailto:jasow...@redhat.com] > > >Sent: Friday, November 28, 2014 3:02 PM > > >To: Du, Fan > > >Cc: net...@vger.kernel.org; da...@davemloft.net

Re: [ovs-dev] Support for MCAST_Snooping

On Tue, Dec 02, 2014 at 07:57:19PM +0530, Aman Kumar wrote: > Hi Flavio, > > I am also working with Neethi Shashidhar > > > You said to Look at the bridge commands mdb/flush and mdb/show at > ovs-vswitch(8) man-page. > > I ran the command "sudo ovs-appctl mdb/show br-int" , this should >

Re: [ovs-dev] Support for MCAST_Snooping

Hi Flavio, I am also working with Neethi Shashidhar > You said to Look at the bridge commands mdb/flush and mdb/show at ovs-vswitch(8) man-page. I ran the command "sudo ovs-appctl mdb/show br-int" , this should show details(like: port, vlan and group) of some hosts which are doing multica

[ovs-dev] adding new ofproto provider

Dear Sirs, I'm working on a project in which the goal is to add a new ofproto provider to ovs while keeping ofproto_dpif. We use ovs version 2.3.0 as base. I created a new ofproto _class (ofproto_new) and I register an instance of this new type of ofproto class in ofproto_init() the same way a

[ovs-dev] Recall: adding new ofproto provider

Zoltán Balogh would like to recall the message, "adding new ofproto provider". ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

[ovs-dev] adding new ofproto provider

Dear Sirs, I'm working on a project in which the goal is to add a new ofproto provider to ovs while keeping ofproto_dpif. We use ovs version I created a new ofproto _class (ofproto_new) and I register an instance of this new type of ofproto class in ofproto_init() the same way as the existing

Re: [ovs-dev] Pass options to systemd openvswitch.service

On Mon, Dec 01, 2014 at 12:53:58PM -0800, Alex Wang wrote: > Sorry for this delayed reply and Thx for the answer, No problem > We'll think of work-arounds I didn't consider the need of having the intermediate steps between the daemons when I did the systemd units, so it made sense to expose a s

Re: [ovs-dev] Support for MCAST_Snooping

On Tue, Dec 02, 2014 at 12:34:26PM +0530, Neethi Shashidhar wrote: > Hi, > > I am currently using the beta version of ovs(2.3.90) and have enabled the > multicast snooping configuration with the help of the link: > http://openvswitch.org/pipermail/dev/2014-June/041775.html > > can you confirm a

[ovs-dev] Understanding different ovs components

Hello,  I am trying to understand different components of ovs. Please correct me if my understanding is wrong,  1. ovsdb-server : Maintains openvswtich configuration databse.  2. ovs-vswitchd : Dameon that controls all Open vSwitch swithces on the local system. When this process is started it ge