[ovs-dev] [PATCH V2 1/1] dpif-netlink: Log eth type 0x1234 not offloadable

2019-07-02 Thread Eli Britstein
Ethernet type 0x1234 is used for testing and not being offloadable. For testing offloadable features, log about using this value. Signed-off-by: Eli Britstein Acked-by: Roi Dayan Signed-off-by: Eli Britstein --- lib/dpif-netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git

Re: [ovs-dev] [PATCH] tnl-neigh-cache: Purge learnt neighbors when port/bridge is deleted

2019-07-02 Thread Vasu Dasari
Hi Flavio, I am trying to emulate the test case scenario you mentioned earlier, where in we need to clean you neighbor cache when an external interface goes down. To study that, I wrote a small script based off of test case system-traffic.at, "datapath - ping over vxlan tunnel". And this

Re: [ovs-dev] [PATCHv5] tunnel: Add layer 2 IPv6 GRE encapsulation support.

2019-07-02 Thread Gregory Rose
On 7/1/2019 12:45 PM, William Tu wrote: The patch adds ip6gre support. Tunnel type 'ip6gre' with packet_type= legacy_l2 is a layer 2 GRE tunnel over IPv6, carrying inner ethernet packets and encap with GRE header with outer IPv6 header. Encapsulation of layer 3 packet over IPv6 GRE, ip6gre, is

Re: [ovs-dev] [PATCHv5] tunnel: Add layer 2 IPv6 GRE encapsulation support.

2019-07-02 Thread Gregory Rose
On 7/2/2019 10:42 AM, Gregory Rose wrote: On 7/1/2019 12:45 PM, William Tu wrote: The patch adds ip6gre support. Tunnel type 'ip6gre' with packet_type= legacy_l2 is a layer 2 GRE tunnel over IPv6, carrying inner ethernet packets and encap with GRE header with outer IPv6 header. 

Re: [ovs-dev] criteria/benchmarks for an improved userspace datapath classifier?

2019-07-02 Thread Michal Orsák
Hello, On 02/07/2019 19:47, Flavio Leitner wrote: On Tue, Jul 02, 2019 at 10:00:44AM -0700, Ben Pfaff wrote: Hi Ilya and Ian. Please allow me to introduce Michal Orsak, a grad student currently looking at packet classifiers. He's implemented a novel classifier that is faster than the one

Re: [ovs-dev] criteria/benchmarks for an improved userspace datapath classifier?

2019-07-02 Thread Michal Orsák
Hello everyone, On 02/07/2019 19:43, Ian Stokes wrote: On 7/2/2019 6:00 PM, Ben Pfaff wrote: Hi Ilya and Ian.  Please allow me to introduce Michal Orsak, a grad student currently looking at packet classifiers.  He's implemented a novel classifier that is faster than the one already in OVS in

Re: [ovs-dev] [PATCH v4 1/3] doc: Move vhost tx retry info to separate section.

2019-07-02 Thread Ian Stokes
On 7/2/2019 1:32 AM, Kevin Traynor wrote: vhost tx retry is applicable to vhost-user and vhost-user-client, but was in the section that compares them. Also, moved further down the doc as prefer to have more fundamental info about vhost nearer the top. Fixes: 6d6513bfc657 ("doc: Add info on

Re: [ovs-dev] [PATCH v2] Detailed packet drop statistics per dpdk and vhostuser ports

2019-07-02 Thread Kevin Traynor
On 02/07/2019 13:30, Sriram Vatala wrote: > Hi Kevin, > > Please consider this as a gentle remainder regarding below mail discussion > and > let me know your thoughts if any. > Hi Sriram, I think your suggested approach is the best available at present i.e. use a more generic name and

Re: [ovs-dev] criteria/benchmarks for an improved userspace datapath classifier?

2019-07-02 Thread Flavio Leitner via dev
On Tue, Jul 02, 2019 at 10:00:44AM -0700, Ben Pfaff wrote: > Hi Ilya and Ian. Please allow me to introduce Michal Orsak, a grad > student currently looking at packet classifiers. He's implemented a > novel classifier that is faster than the one already in OVS in the > benchmarks that he's run.

Re: [ovs-dev] criteria/benchmarks for an improved userspace datapath classifier?

2019-07-02 Thread Ian Stokes
On 7/2/2019 6:00 PM, Ben Pfaff wrote: Hi Ilya and Ian. Please allow me to introduce Michal Orsak, a grad student currently looking at packet classifiers. He's implemented a novel classifier that is faster than the one already in OVS in the benchmarks that he's run. His classifier is

Re: [ovs-dev] [PATCHv5] tunnel: Add layer 2 IPv6 GRE encapsulation support.

2019-07-02 Thread Gregory Rose
On 7/1/2019 12:45 PM, William Tu wrote: The patch adds ip6gre support. Tunnel type 'ip6gre' with packet_type= legacy_l2 is a layer 2 GRE tunnel over IPv6, carrying inner ethernet packets and encap with GRE header with outer IPv6 header. Encapsulation of layer 3 packet over IPv6 GRE, ip6gre, is

Re: [ovs-dev] [PATCH 1/1] dpif-netlink: Warn eth type 0x1234 not offloadable

2019-07-02 Thread Ben Pfaff
On Sun, Jun 30, 2019 at 06:16:05AM +, Eli Britstein wrote: > Ethernet type 0x1234 is used for testing and not being offloadable. For > testing offloadable features, warn about using this value. > > Signed-off-by: Eli Britstein > --- > lib/dpif-netlink.c | 1 + > 1 file changed, 1

[ovs-dev] criteria/benchmarks for an improved userspace datapath classifier?

2019-07-02 Thread Ben Pfaff
Hi Ilya and Ian. Please allow me to introduce Michal Orsak, a grad student currently looking at packet classifiers. He's implemented a novel classifier that is faster than the one already in OVS in the benchmarks that he's run. His classifier is tree-based, like most high-performance

Re: [ovs-dev] [PATCH v9 1/5] dpif-netdev: implement function pointers/subtable

2019-07-02 Thread Ian Stokes
On 7/2/2019 4:02 PM, Van Haaren, Harry wrote: -Original Message- From: Stokes, Ian Sent: Tuesday, July 2, 2019 3:40 PM To: Van Haaren, Harry ; ovs-dev@openvswitch.org Cc: i.maxim...@samsung.com Subject: Re: [ovs-dev] [PATCH v9 1/5] dpif-netdev: implement function pointers/subtable On

Re: [ovs-dev] [PATCHv13] netdev-afxdp: add new netdev type for AF_XDP.

2019-07-02 Thread Ilya Maximets
On 28.06.2019 19:37, William Tu wrote: >> >> >> One more thing I noticed is the same issue as you had with completion queue, >> but >> with rx queue. When I'm trying to send traffic from 2 threads to the same >> port, > > Is the 2 threads send traffic using afxdp tx? Yes. > >> I'm starting

Re: [ovs-dev] [PATCH v9 1/5] dpif-netdev: implement function pointers/subtable

2019-07-02 Thread Van Haaren, Harry
> -Original Message- > From: Stokes, Ian > Sent: Tuesday, July 2, 2019 3:40 PM > To: Van Haaren, Harry ; ovs-dev@openvswitch.org > Cc: i.maxim...@samsung.com > Subject: Re: [ovs-dev] [PATCH v9 1/5] dpif-netdev: implement function > pointers/subtable > > On 5/15/2019 6:02 PM, Ian Stokes

Re: [ovs-dev] [PATCH v9 1/5] dpif-netdev: implement function pointers/subtable

2019-07-02 Thread Ian Stokes
On 5/15/2019 6:02 PM, Ian Stokes wrote: On 5/8/2019 4:13 PM, Harry van Haaren wrote: This allows plugging-in of different subtable hash-lookup-verify routines, and allows special casing of those functions based on known context (eg: # of bits set) of the specific subtable. Signed-off-by: Harry

Re: [ovs-dev] [PATCH v2] Detailed packet drop statistics per dpdk and vhostuser ports

2019-07-02 Thread Sriram Vatala via dev
Hi Kevin, Please consider this as a gentle remainder regarding below mail discussion and let me know your thoughts if any. Thanks & Regards, Sriram. -Original Message- From: Sriram Vatala Sent: 26 June 2019 11:01 To: 'Venkatesan Pradeep' ; 'Kevin Traynor' ; 'ovs-dev@openvswitch.org'

Re: [ovs-dev] [Suspected-Phishing]Re: [Suspected-Phishing]Re: [PATCH v2 1/3] netdev: Dynamic per-port Flow API.

2019-07-02 Thread Roi Dayan
On 2019-07-02 2:23 PM, Roi Dayan wrote: >>> Regarding deprecation, I'd like to remove all the functionality from >>> ovs-dpctl >>> utility keeping only ability to remove system datapaths, since this, IMHO, >>> is the only useful function. >>> Imagine some flows are in TC and some in OVS.

Re: [ovs-dev] [Suspected-Phishing]Re: [Suspected-Phishing]Re: [Suspected-Phishing] [PATCH 1/1] dpif-netlink: Warn eth type 0x1234 not offloadable

2019-07-02 Thread Roi Dayan
On 2019-07-02 2:33 PM, Roi Dayan wrote: > > > On 2019-07-02 2:21 PM, Roi Dayan wrote: >> >> >> On 2019-06-30 9:16 AM, Eli Britstein wrote: >>> Ethernet type 0x1234 is used for testing and not being offloadable. For >>> testing offloadable features, warn about using this value. >>> >>>

Re: [ovs-dev] [Suspected-Phishing] [PATCH 1/1] dpif-netlink: Warn eth type 0x1234 not offloadable

2019-07-02 Thread Roi Dayan
On 2019-06-30 9:16 AM, Eli Britstein wrote: > Ethernet type 0x1234 is used for testing and not being offloadable. For > testing offloadable features, warn about using this value. > > Signed-off-by: Eli Britstein > --- > lib/dpif-netlink.c | 1 + > 1 file changed, 1 insertion(+) > > diff

Re: [ovs-dev] [Suspected-Phishing]Re: [Suspected-Phishing] [PATCH 1/1] dpif-netlink: Warn eth type 0x1234 not offloadable

2019-07-02 Thread Roi Dayan
On 2019-07-02 2:21 PM, Roi Dayan wrote: > > > On 2019-06-30 9:16 AM, Eli Britstein wrote: >> Ethernet type 0x1234 is used for testing and not being offloadable. For >> testing offloadable features, warn about using this value. >> >> Signed-off-by: Eli Britstein >> --- >> lib/dpif-netlink.c

Re: [ovs-dev] [Suspected-Phishing]Re: [PATCH v2 1/3] netdev: Dynamic per-port Flow API.

2019-07-02 Thread Roi Dayan
On 2019-07-01 1:53 PM, Eli Britstein wrote: > > On 7/1/2019 1:46 PM, Ilya Maximets wrote: >> On 01.07.2019 13:24, Eli Britstein wrote: >>> On 7/1/2019 1:13 PM, Ilya Maximets wrote: On 30.06.2019 7:47, Eli Britstein wrote: > This patch breaks ovs-dpctl dump-flows, when using TC

Re: [ovs-dev] [PATCH v2] vswitchd: Always cleanup userspace datapath.

2019-07-02 Thread Ilya Maximets
On 01.07.2019 19:52, Ben Pfaff wrote: > On Thu, Jun 27, 2019 at 08:24:46PM +0300, Ilya Maximets wrote: >> On 26.06.2019 21:27, Ben Pfaff wrote: >>> On Tue, Jun 25, 2019 at 01:12:11PM +0300, Ilya Maximets wrote: 'netdev' datapath is implemented within ovs-vswitchd process and can not

Re: [ovs-dev] [PATCH] netdev-offload-tc: Fix requesting match on wildcarded vlan tpid.

2019-07-02 Thread Ilya Maximets
On 19.06.2019 12:16, Ilya Maximets wrote: > 'mask' must be checked first before configuring key in flower. > > CC: Eli Britstein > Fixes: 0b0a84783cd6 ("netdev-tc-offloads: Support match on priority tags") > Signed-off-by: Ilya Maximets > --- > lib/netdev-offload-tc.c | 8 ++-- > 1 file

Re: [ovs-dev] [PATCH] NEWS: Update regarding dumping HW offloaded flows.

2019-07-02 Thread Ilya Maximets
On 01.07.2019 13:52, Ilya Maximets wrote: > NEWS update was missed while updating docs for dynamic Flow API. > Since this is a user visible change, it should be mentioned here. > > Fixes: d74ca2269e36 ("dpctl: Update docs about dump-flows and HW offloading.") > Signed-off-by: Ilya Maximets > ---

[ovs-dev] B2B COLLABORATION (BUYING)

2019-07-02 Thread Juthamas Joy Loveyou via dev
Sainsbury's is the UK's second largest supermarket chain. It offers a wide range of other products. Sainsbury's started e-commerce home delivery operations in 1995. In 1996, on Monday 30 December it was announced that Sainsbury's has joined forces with Hewlett-Packard for the development of an

Re: [ovs-dev] [PATCH v3 3/3] ovn: Send GARP for router port IPs of a router port connected to bridged logical switch

2019-07-02 Thread Dumitru Ceara
On Mon, Jul 1, 2019 at 9:45 AM wrote: > > From: Numan Siddique > > This patch handles sending GARPs for > > - router port IPs of a distributed router port > > - router port IPs of a router port which belongs to gateway router >(with the option - redirect-chassis set in

Re: [ovs-dev] [PATCH v4 0/3] vhost tx retry updates

2019-07-02 Thread Eelco Chaudron
On 2 Jul 2019, at 2:32, Kevin Traynor wrote: > v4: > - 1/2 New patch: Move vhost tx retries doc to a seperate section (David) > > - 2/3 > -- Changed tx_retries to be a custom stat for vhost (Ilya) > -- Added back in MIN() that was dropped in v2, as in retesting I >saw it is needed when the

[ovs-dev] [PATCH 4/4] OVN: Add IGMP tests

2019-07-02 Thread Dumitru Ceara
Signed-off-by: Dumitru Ceara --- tests/ovn.at | 270 ++ 1 file changed, 270 insertions(+) diff --git a/tests/ovn.at b/tests/ovn.at index daf85a5..aa8c46f 100644 --- a/tests/ovn.at +++ b/tests/ovn.at @@ -14017,3 +14017,273 @@ ovn-hv4-0

[ovs-dev] [PATCH 3/4] OVN: Add ovn-northd IGMP support

2019-07-02 Thread Dumitru Ceara
New IP Multicast Snooping Options are added to the Northbound DB Logical_Switch:other_config column. These allow enabling IGMP snooping and querier on the logical switch and get translated by ovn-northd to rows in the IP_Multicast Southbound DB table. ovn-northd monitors for changes done by

[ovs-dev] [PATCH 2/4] OVN: Add IGMP SB definitions and ovn-controller support

2019-07-02 Thread Dumitru Ceara
A new IP_Multicast table is added to Southbound DB. This table stores the multicast related configuration for each datapath. Each row will be populated by ovn-northd and will control: - if IGMP Snooping is enabled or not, the snooping table size and multicast group idle timeout. - if IGMP

[ovs-dev] [PATCH 0/4] OVN: Add IGMP support

2019-07-02 Thread Dumitru Ceara
This series introduces support for IGMP Snooping and IGMP Querier. IGMP versions v1-v3 are supported for snooping and IGMP queries originated by ovn-controller are general IGMPv3 queries. The rationale behind using v3 for querier is that it's backward compatible with v1-v2. The majority of the

[ovs-dev] [PATCH 1/4] packets: Add IGMPv3 query packet definitions

2019-07-02 Thread Dumitru Ceara
Signed-off-by: Dumitru Ceara --- lib/packets.c | 44 lib/packets.h | 19 ++- 2 files changed, 62 insertions(+), 1 deletion(-) diff --git a/lib/packets.c b/lib/packets.c index a8fd61f..ab0b1a3 100644 --- a/lib/packets.c +++

[ovs-dev] [PATCH 1/1] ovsdb-idl: fix memory leak for the memory allocated in ovsdb_idl_column.parse() functions.

2019-07-02 Thread Damjan Skvarc
"make check-valgrind" points to memory leak issue in case memory is allocated within one of ovsdb_idl_column.parse() functions. More details can be found in pull request https://github.com/openvswitch/ovs/pull/290. Each issue can be solved in many different ways. This one was solved by modifying