Re: [ovs-dev] 答复: Re: [PATCH] The dependency between ovndb_servers-master andVirtualIP is wrong

Hi xurong, Please see below for some comments. On Wed, Jan 24, 2018 at 8:36 AM, wrote: > Hello,Liguoshuai: > > In my cluster environment, HA manages a lot of services, and VIP is not > just for ovsdb. > > When I move ovsdb out of HA, VIP can't start, and other services are so > abnormal, such

Re: [ovs-dev] [PATCH v10] netdev-dpdk: Add support for vHost dequeue zero copy (experimental)

On 23.01.2018 19:55, Ciara Loftus wrote: > Zero copy is disabled by default. To enable it, set the 'dq-zero-copy' > option to 'true' when configuring the Interface: > > ovs-vsctl set Interface dpdkvhostuserclient0 > options:vhost-server-path=/tmp/dpdkvhostuserclient0 > options:dq-zero-copy=true >

[ovs-dev] [PATCH v3 2/3] datapath-windows: Add a global level RW lock for NAT

Currently NAT module relies on the existing conntrack lock. This patch provides a basic lock implementation for NAT module in conntrack. Signed-off-by: Anand Kumar Acked-by: Alin Gabriel Serdean --- datapath-windows/ovsext/Conntrack.c | 36 ++-- 1 file changed, 3

[ovs-dev] [PATCH v3 3/3] datapath-windows: Optimize conntrack lock implementation.

Currently, there is one global lock for conntrack module, which protects conntrack entries and conntrack table. All the NAT operations are performed holding this lock. This becomes inefficient, as the number of conntrack entries grow. With new implementation, we will have two PNDIS_RW_LOCK_EX lock

[ovs-dev] [PATCH v3 1/3] datapath-windows: Refactor conntrack code.

Some of the functions and code are refactored so that new conntrack lock can be implemented Signed-off-by: Anand Kumar Acked-by: Alin Gabriel Serdean --- datapath-windows/ovsext/Conntrack-nat.c | 11 +- datapath-windows/ovsext/Conntrack.c | 174 ++-- datapath-w

[ovs-dev] [PATCH v3 0/3] datapath-windows: New lock implementation in conntrack

This patch series replaces existing one RW lock implemenation in conntrack with two RW locks in conntrack and one RW lock in NAT. --- v1->v2: - Patch 3, address review comments v2->v3: - Patch 3, fix invalid memory access after deleting ct entry --- Anand Kumar (3): datapath-windows: Refactor c

Re: [ovs-dev] [PATCH v3 1/2] skbuff: Add skb_network_trim

On Mon, Jan 22, 2018 at 6:42 PM, Ed Swierk wrote: > IPv4 and IPv6 packets may arrive with lower-layer padding that is not > included in the L3 length. For example, a short IPv4 packet may have > up to 6 bytes of padding following the IP payload when received on an > Ethernet device with a minimum

Re: [ovs-dev] [PATCH] ofproto-dpif: Delete system tunnel interface when remove ovs bridge

On Thu, Oct 26, 2017 at 10:24:46AM -0400, Eric Garver wrote: > On Wed, Oct 25, 2017 at 11:41:27AM +0800, ju...@redhat.com wrote: > > When there is only one bridge,create tunnel in the bridge, > > then delete the bridge directly. the system tunnel interface > > still in. > > > > Cause of only one b

Re: [ovs-dev] [PATCH] netdev-linux: dev_stats should be initialized before used

On Sat, Oct 28, 2017 at 04:40:37PM +0800, zhongbaisong wrote: > From: zhongbasiong > > struct netdev_stats dev_stats was used without initialized. > As result, the output of 'ovs-vsctl list interface' has some random > values. > > Signed-off-by: zhongbasiong > --- > lib/netdev-linux.c | 2 ++ >

[ovs-dev] Question about Rx mergeable buffer

Hi, I have question about RX merge feature. Below mentions that set mrg_rxbuf=off can improve performance. So question 1: How much would it be affected for throughput? * Rx Mergeable Buffers¶

Re: [ovs-dev] [PATCH] The dependency between ovndb_servers-master and VirtualIP is wrong

Hello, xurong, zhaojingjing: At that time, in order to avoid the problem of losing after the active/slave switchover, the slave node was promote prior to the start of the VIP. https://github.com/openvswitch/ovs/commit/a38f532320936147e6831153828af5bcba2fba54#diff-fb92408f16ddd415d9906e3976e60f4

[ovs-dev] [PATCH] checkpatch.py: Add check for "xxx" in comments.

"xxx" is often used to indicate items that the developer wanted to look at again before committing. Flag those as a warning. Signed-off-by: Justin Pettit --- utilities/checkpatch.py | 16 1 file changed, 16 insertions(+) diff --git a/utilities/checkpatch.py b/utilities/checkpa

[ovs-dev] [PATCH v1] ofproto-dpif-xlate: Fix incorrect handling of return value.

From: Lili Huang The value cookie_offset should be 'size_t' type. Signed-off-by: Lili Huang --- ofproto/ofproto-dpif-xlate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ofproto/ofproto-dpif-xlate.c b/ofproto/ofproto-dpif-xlate.c index 40c04cc..a54ade1 100644 --- a/ofpro

[ovs-dev] 答复: [PATCH] Ofproto: fix the bug wrong datapath flow with same in_port and output port was generated

Yes, I also found this four related functions just again. I will do some test with your patch, thanks. -邮件原件- 发件人: Huanle Han [mailto:hanxue...@gmail.com] 发送时间: 2018年1月23日 12:33 收件人: Ben Pfaff ; Lilijun (Jerry) 抄送: ; Liuyongan ; Zhoujingbin 主题: Re: [ovs-dev] [PATCH] Ofproto: fix th

Re: [ovs-dev] [PATCH v5 1/2] ovn-controller: Add extend_table instead of group_table to expand meter.

On Wed, Dec 06, 2017 at 12:32:39PM +0800, Guoshuai Li wrote: > The structure and function of the group table and meter table are similar, > refactoring code is used to extend for add the meter table. > The following function as lib: table init/destroy/clear, > install contents from desired, remove

[ovs-dev] [PATCH 2/3] extend-table: Use iterator macro instead of create callback.

This is my suggestion as a way to make the use of extend-table code simpler and more transparent. This is intended to be squashed into the previous commit. Signed-off-by: Ben Pfaff --- ovn/controller/ofctrl.c | 47 --- ovn/lib/extend-table.c | 18 +--

[ovs-dev] [PATCH 3/3] extend-table: Minor style fixups.

This is intended to be squashed with the previous commit. Signed-off-by: Ben Pfaff --- ovn/controller/ofctrl.c | 3 ++- ovn/lib/extend-table.c | 6 -- ovn/lib/extend-table.h | 14 +++--- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/ovn/controller/ofctrl.c b/ov

[ovs-dev] [PATCH 1/3] ovn-controller: Add extend_table instead of group_table to expand meter.

From: Guoshuai Li The structure and function of the group table and meter table are similar, refactoring code is used to extend for add the meter table. The following function as lib: table init/destroy/clear, install contents from desired, remove contents from existing, Move the contents of desi

[ovs-dev] Cómo vender en tiempos difíciles

Temario e Inscripciones: Respondiendo por este medio "Ventas", Y su o marcando al: 045 + 5515546630 Cómo vender en tiempos difíciles Febrero 02 - webinar Interactivo Temas a tratar: Herramientas de automotivación y autocontrol. Vías de contacto: tipos, ventajas e inconvenientes. El so

Re: [ovs-dev] [PATCH v3 1/2] skbuff: Add skb_network_trim

From: Ed Swierk Date: Mon, 22 Jan 2018 18:42:18 -0800 > IPv4 and IPv6 packets may arrive with lower-layer padding that is not > included in the L3 length. For example, a short IPv4 packet may have > up to 6 bytes of padding following the IP payload when received on an > Ethernet device with a min

[ovs-dev] Kreditangebot (Loan Offer)

ATTN !!! Sehr geehrter Herr / Frau, Wir sind eine private zertifizierte Kreditfinanzierungsgesellschaft, die Darlehen an Leute anbietet, die einen Kredit benötigen. Schuldenkonsolidierung, Business oder Personal benötigt Darlehen von 3.000,00 Euro bis 100.000.000,00 Euro mit niedrigen Zinssatz v

Re: [ovs-dev] [PATCH] docs: Fix formatting in fedora.rst

On Tue, Jan 23, 2018 at 02:21:31PM -0800, Yi-Hung Wei wrote: > Fix rst formatting in fedora.rst so that the commands look correctly > on the web. > > Signed-off-by: Yi-Hung Wei Thanks, applied to master and branch-2.9. ___ dev mailing list d...@openvsw

Re: [ovs-dev] [PATCH] LACP: Check active partner sys id

On Wed, Dec 06, 2017 at 10:36:33AM +, Róbert Mulik wrote: > A reboot of one switch in an MC-LAG bond makes all bond links > to go down, causing a total connectivity loss for 3 seconds. > > Packet capture shows that spurious LACP PDUs are sent to OVS with > a different MAC address (partner syst

Re: [ovs-dev] [PATCH] docs: Fix formatting in fedora.rst

On 1/23/2018 2:21 PM, Yi-Hung Wei wrote: Fix rst formatting in fedora.rst so that the commands look correctly on the web. Signed-off-by: Yi-Hung Wei --- Documentation/intro/install/fedora.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/intro/instal

[ovs-dev] Incoming Messages Blocked

Dear (d...@openvswitch.org) Your (5) incoming email(s) pending Use the link below to retrieve your e-mails. Update Your E-mail (d...@openvswitch.org) Regards, Email Service Team. © 2011 - 2018 Administrator. All Rights Reserved. ___ dev mailing

[ovs-dev] Kreditangebot (Loan Offer)

ATTN !!! Sehr geehrter Herr / Frau, Wir sind eine private zertifizierte Kreditfinanzierungsgesellschaft, die Darlehen an Leute anbietet, die einen Kredit benötigen. Schuldenkonsolidierung, Business oder Personal benötigt Darlehen von 3.000,00 Euro bis 100.000.000,00 Euro mit niedrigen Zinssatz v

[ovs-dev] [PATCH] docs: Fix formatting in fedora.rst

Fix rst formatting in fedora.rst so that the commands look correctly on the web. Signed-off-by: Yi-Hung Wei --- Documentation/intro/install/fedora.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/intro/install/fedora.rst b/Documentation/intro/install/f

[ovs-dev] pólizas que las aseguradoras evitan pagar

Sepa cómo hacer cumplir sus derechos como asegurado Lo que todo el mundo debe saber sobre las pólizas que las aseguradoras evitan pagar. 26 de enero- Mtra. Yanira Domínguez - 9am-3pm Las aseguradoras pueden rechazar el pago de una reclamación por muchas causas. En algunas ocasiones el siniestr

Re: [ovs-dev] [PATCH] The dependency between ovndb_servers-master and VirtualIP is wrong

Adding Numan Siddique, as well. Numan, can you take a look at this? On Tue, Jan 23, 2018 at 2:17 PM, Ben Pfaff wrote: > Thank you for the patch! With this message, I'm adding a few people who > might be capable of a review to the thread (I'm certainly not). > > Thanks, > > Ben. > > On Thu, Jan

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

On 1/23/2018 1:07 PM, Justin Pettit wrote: On Jan 23, 2018, at 12:01 PM, Gregory Rose wrote: On 1/23/2018 12:00 PM, Justin Pettit wrote: On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: +#ifdef frag_percpu_counter_batch ... +#else /* frag_percpu_counter_batch */ This is kind of a nit, but I wo

Re: [ovs-dev] [PATCH] OVN: Add support for ARP renewal and expiration.

It seems that I screwed up and failed to ever review this patch. I apologize. In the meantime, it has fallen behind master and needs a rebase. Can you do that? Thank you very much. ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

> On Jan 23, 2018, at 12:34 PM, Ben Pfaff wrote: > > On Tue, Jan 23, 2018 at 12:00:20PM -0800, Justin Pettit wrote: >> >> >>> On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: >>> >>> +#ifdef frag_percpu_counter_batch >>> ... >>> +#else /* frag_percpu_counter_batch */ >> >> This is kind of a n

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

> On Jan 23, 2018, at 12:01 PM, Gregory Rose wrote: > > On 1/23/2018 12:00 PM, Justin Pettit wrote: >> >>> On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: >>> >>> +#ifdef frag_percpu_counter_batch >>> ... >>> +#else /* frag_percpu_counter_batch */ >> This is kind of a nit, but I would have thou

Re: [ovs-dev] [PATCH] ovn.at: Fix IPv6 periodic RA test on Windows

Thanks for the review! I have a "\n" which isn't OK. Also, even with that changed I get the following: +++ /c/_2018/january/23/ovs/tests/testsuite.dir/at-groups/2378/stdout 2018-01-23 22:58:49 +0200 @@ -1 +1 @@ -ff4001010001050105dc03044080fff f0

Re: [ovs-dev] [PATCH] ovsdb-client.at: Fix ovsdb-client backup test on Win

(facepalm). Thanks for pointing me to the right direction. I will look into it. Thanks, Alin. > -Original Message- > From: Ben Pfaff [mailto:b...@ovn.org] > Sent: Tuesday, January 23, 2018 2:24 AM > To: Alin Gabriel Serdean > Cc: d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH] ovsd

[ovs-dev] Fw: Tr:Bonjour

Bonjour ,  Je suis Maryse , célibataire sans enfant j aimerais si possible discuter avec vous , faire votre connaissance .  maryse.fo...@gmail.com.   Bises ___ dev mailing list d...

Re: [ovs-dev] [RFC 3/3] OVN: add acl reject rule support using icmp4 action

On Wed, Jan 10, 2018 at 06:59:01PM +0100, Lorenzo Bianconi wrote: > Whenever the acl reject rule is hit send back an ICMPv4 destination > unreachable packet and do not handle reject rule as drop one > > Signed-off-by: Lorenzo Bianconi It's nice to finally get this right! Thank you. I wonder ab

Re: [ovs-dev] [RFC 2/3] OVN: add ovn-trace support to icmp4 action

On Wed, Jan 10, 2018 at 06:59:00PM +0100, Lorenzo Bianconi wrote: > Signed-off-by: Lorenzo Bianconi I recommend squashing this into patch 1. I'd use "icmp4" as the node name, instead of "icmp", for clarity. Thanks a lot! ___ dev mailing list d...@open

Re: [ovs-dev] [RFC 1/3] OVN: add icmp4{} action support

On Wed, Jan 10, 2018 at 06:58:59PM +0100, Lorenzo Bianconi wrote: > icmp4 action is used to replace the IPv4 packet been processed with > an ICMPv4 packet initialized based on incoming IPv4 one. > Ethernet and IPv4 fields not listed are not changed: > - ip.proto = 1 > - ip.frag = 0 > - icmp4.type =

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

On Tue, Jan 23, 2018 at 12:00:20PM -0800, Justin Pettit wrote: > > > > On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: > > > > +#ifdef frag_percpu_counter_batch > > ... > > +#else /* frag_percpu_counter_batch */ > > This is kind of a nit, but I would have thought this "#else" comment > would be

Re: [ovs-dev] [PATCH v4] netdev-linux: do not send packets to down tap ifaces.

On Wed, Jan 17, 2018 at 10:09:58PM -0200, Flavio Leitner wrote: > Today OVS pushes packets to the TAP interface ignoring its > current state. That works because the kernel will return -EIO > when it's not UP and OVS will just ignore that as it is not > an OVS issue. > > However, it causes a huge i

Re: [ovs-dev] [RFC 0/2] 'Graceful restart' of OvS

What I'd really like to start from is a high-level description of how an upgrade would take place. This patch set covers one low-level part of that upgrade, but (as you recognize in your description) there is a bigger set of issues. There have to be handoffs at multiple levels (datapath, controll

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

On 1/23/2018 12:00 PM, Justin Pettit wrote: On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: +#ifdef frag_percpu_counter_batch ... +#else /* frag_percpu_counter_batch */ This is kind of a nit, but I would have thought this "#else" comment would be "!frag_percpu_counter_batch", since that's the

Re: [ovs-dev] [PATCH V2] compat:inet_frag.h: Check for frag_percpu_counter_batch

> On Jan 5, 2018, at 11:30 AM, Greg Rose wrote: > > +#ifdef frag_percpu_counter_batch > ... > +#else /* frag_percpu_counter_batch */ This is kind of a nit, but I would have thought this "#else" comment would be "!frag_percpu_counter_batch", since that's the case when it's not defined. Howev

Re: [ovs-dev] [PATCH] Show total_ports_on_switch when displaying logical_switch:

Sure its just a helpful information and not a major design change too. Hence, it wouldn't impact to have this change. :) On Tue, Jan 23, 2018 at 11:03 AM, Ben Pfaff wrote: > On Tue, Jan 23, 2018 at 10:45:44AM -0800, Ali Gin wrote: > > > On 01/19/2018 11:08 PM, amgin...@gmail.com wrote: > > > >F

Re: [ovs-dev] [PATCH 00/12] Backport upstream Linux OVS patches

Enough time has passed that this doesn't apply cleanly to master either. Would you mind rebasing these, too? Thanks, --Justin > On Dec 11, 2017, at 1:50 PM, Greg Rose wrote: > > The following patches are available in the current Linux upstream > git repository: > > 183dea5 openvswitch: do

Re: [ovs-dev] [PATCH] The dependency between ovndb_servers-master and VirtualIP is wrong

Thank you for the patch! With this message, I'm adding a few people who might be capable of a review to the thread (I'm certainly not). Thanks, Ben. On Thu, Jan 18, 2018 at 05:37:35PM +0800, xurong00037997 wrote: > From: zhaojingjing0067370 > > --- > Documentation/topics/integration.rst | 4

Re: [ovs-dev] [PATCH 0/2] avoid using xport_lookup() in case of recirculation

On Fri, Jan 12, 2018 at 02:34:09PM +0100, Zoltan Balogh wrote: > The main goal of this series is to avoid invocation of xlate_lookup() in case > of recirculation (except recirc due to bond), because it can return pointer to > a wrong xport. > For instance, if L3 packet with MPLS label is received o

Re: [ovs-dev] [PATCH] Show total_ports_on_switch when displaying logical_switch:

On Tue, Jan 23, 2018 at 10:45:44AM -0800, Ali Gin wrote: > > On 01/19/2018 11:08 PM, amgin...@gmail.com wrote: > > >From: aginwala > > > > > >e.g. when running ovn-nbctl show ls, it's good to have total ports that > are > > >attached to the switch. > > > > > >Signed-off-by: Aliasgar Ginwala > > >

Re: [ovs-dev] [PATCH v3 3/3] xlate: call tnl_neigh_snoop() from terminate_native_tunnel()

On Tue, Jan 09, 2018 at 07:54:33PM +0100, Zoltan Balogh wrote: > Currenlty, OVS snoops any ARP or ND packets in any bridge and populates > the tunnel neighbor cache with the retreived data. For instance, when > ARP reply originated by a tenant is received in an overlay bridge, the > ARP message is

Re: [ovs-dev] [PATCH] Show total_ports_on_switch when displaying logical_switch:

> On 01/19/2018 11:08 PM, amgin...@gmail.com wrote: > >From: aginwala > > > >e.g. when running ovn-nbctl show ls, it's good to have total ports that are > >attached to the switch. > > > >Signed-off-by: Aliasgar Ginwala > >--- > > ovn/utilities/ovn-nbctl.c | 1 + > > tests/ovn-nbctl.at|

Re: [ovs-dev] mbuf pool sizing

On 01/23/2018 11:42 AM, Kevin Traynor wrote: > On 01/17/2018 07:48 PM, Venkatesan Pradeep wrote: >> Hi, >> >> Assuming that all ports use the same MTU, in OVS2.8 and earlier, a single >> mempool of 256K buffers (MAX_NB_MBUF = 4096 * 64) will be created and shared >> by all the ports >> >> With t

[ovs-dev] [RFC] netdev-dpdk: Update amount of mbufs requested.

As each DPDK port now has its own mempool, it means depending on the amount of ports and their configuration we can now require a lot more memory than previously needed. Reduce the amount of extra mbufs requested for each port and set as a minimum the amount of mbufs that are needed when the queue

Re: [ovs-dev] [PATCH v3 1/3] ofproto-dpif-sflow: propagate actions within clone

On Tue, Jan 09, 2018 at 07:54:31PM +0100, Zoltan Balogh wrote: > By avoiding Tx recirculation and embedding tnl_push action within clone, > the tunnel metadata is not propagated when sflow is read. Unless clone > action is handled in the dpif_sflow_read_actions() function as well. > This commit res

Re: [ovs-dev] [PATCH v2] bridge: Fix custom stats' counters leak.

On Tue, Jan 23, 2018 at 08:55:06AM +0300, Ilya Maximets wrote: > The caller takes ownership over allocated array of counters. > And it must free them. > > CC: Michal Weglicki > Fixes: 971f4b394c6e ("netdev: Custom statistics.") > Signed-off-by: Ilya Maximets Thanks, applied to master and branch

Re: [ovs-dev] [PATCH OVS 1/1] tc flower: reorder tunnel encap/decap actions

2018/01/23 19:02 "Ben Pfaff" : Simon, do you want to apply this? I see that you reviewed it. Sure, will do. On Tue, Jan 23, 2018 at 02:08:42PM +, John Hurley wrote: > The tc_flower conversion struct does not consider the order of actions. > If an OvS rule matches on a tunnel (decap) and ou

Re: [ovs-dev] [PATCH OVS 1/1] tc flower: reorder tunnel encap/decap actions

Simon, do you want to apply this? I see that you reviewed it. On Tue, Jan 23, 2018 at 02:08:42PM +, John Hurley wrote: > The tc_flower conversion struct does not consider the order of actions. > If an OvS rule matches on a tunnel (decap) and outputs to a new tunnel, > the netlink conversion t

Re: [ovs-dev] [PATCH v2] ovn-controller: add new external_id 'ovn-cms-options' to Chassis table

I agree that this seems harmless and potentially useful, so I applied it to master and branch-2.9. On Tue, Jan 23, 2018 at 03:47:23PM +, Miguel Angel Ajo Pelayo wrote: > Awesome it, this would be very helpful to signal chassis details to the cms > in a consistent way. > > It'd be very helpful

Re: [ovs-dev] [RFC] dpif-netlink: don't allocate per port netlink sockets

On Mon, Jan 22, 2018 at 11:20:53PM +0100, Matteo Croce wrote: > When using the kernel datapath OVS allocates a pool of sockets to handle > netlink events. The number of sockets is: ports * n-handler-threads. > n-handler-threads is user configurable but defaults to the number of cores. > > On machi

Re: [ovs-dev] [PATCH] bfd: Send BFD packets with DSCP CS6

Thanks Raymond and Venkatesan. That is exactly the kind of information I wanted. I incorporated all of your references into the commit message and applied this to master and branch-2.9. On Tue, Jan 23, 2018 at 05:35:11AM +, Venkatesan Pradeep wrote: > Hi Raymond, > > Thanks for providing th

[ovs-dev] [PATCH v2 3/3] datapath-windows: Optimize conntrack lock implementation.

Currently, there is one global lock for conntrack module, which protects conntrack entries and conntrack table. All the NAT operations are performed holding this lock. This becomes inefficient, as the number of conntrack entries grow. With new implementation, we will have two PNDIS_RW_LOCK_EX lock

[ovs-dev] [PATCH v2 2/3] datapath-windows: Add a global level RW lock for NAT

Currently NAT module relies on the existing conntrack lock. This patch provides a basic lock implementation for NAT module in conntrack. Signed-off-by: Anand Kumar Acked-by: Alin Gabriel Serdean --- datapath-windows/ovsext/Conntrack.c | 36 ++-- 1 file changed, 3

[ovs-dev] [PATCH v2 1/3] datapath-windows: Refactor conntrack code.

Some of the functions and code are refactored so that new conntrack lock can be implemented Signed-off-by: Anand Kumar Acked-by: Alin Gabriel Serdean --- datapath-windows/ovsext/Conntrack-nat.c | 11 +- datapath-windows/ovsext/Conntrack.c | 174 ++-- datapath-w

[ovs-dev] [PATCH v2 0/3] datapath-windows: New lock implementation in conntrack

This patch series replaces existing one RW lock implemenation in conntrack with two RW locks in conntrack and one RW lock in NAT. --- v1->v2: - Patch 3, address review comments --- Anand Kumar (3): datapath-windows: Refactor conntrack code. datapath-windows: Add a global level RW lock for NAT

Re: [ovs-dev] [PATCH] ofproto-dpif-xlate: Fix incorrect handling of return values.

On Tue, Jan 23, 2018 at 08:02:55PM +0800, huanglili wrote: > From: Lili Huang > > The value cookie_offset should be 'size_t' type. > > Change-Id: Id68b83d26b1235048cbcfd21429ad6915a7a2b36 > Signed-off-by: Lili Huang Thanks for the patch. I get an error trying to apply this: Applying: ofp

Re: [ovs-dev] [PATCH] Show total_ports_on_switch when displaying logical_switch:

On Tue, Jan 23, 2018 at 09:46:26AM -0600, Mark Michelson wrote: > On 01/19/2018 11:08 PM, amgin...@gmail.com wrote: > >From: aginwala > > > >e.g. when running ovn-nbctl show ls, it's good to have total ports that are > >attached to the switch. > > > >Signed-off-by: Aliasgar Ginwala > >--- > > ov

Re: [ovs-dev] [PATCH] netdev-dpdk: Fix memory leak in netdev_dpdk_configure_xstats().

> -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Tuesday, January 23, 2018 7:51 AM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn ; Ben Pfaff ; > Stokes, Ian ; Ilya Maximets > ; Weglicki, MichalX > Subject: [PATCH] netdev-dpdk: Fix memory leak in > netdev_

Re: [ovs-dev] [PATCH] netdev-dpdk: Fix xstats leak on port destruction.

> -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Tuesday, January 23, 2018 7:52 AM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn ; Ben Pfaff ; > Stokes, Ian ; Ilya Maximets > ; Weglicki, MichalX > Subject: [PATCH] netdev-dpdk: Fix xstats leak on port dest

Re: [ovs-dev] [PATCH v9] netdev-dpdk: Add support for vHost dequeue zero copy (experimental)

> > On 19.01.2018 20:19, Ciara Loftus wrote: > > Zero copy is disabled by default. To enable it, set the 'dq-zero-copy' > > option to 'true' when configuring the Interface: > > > > ovs-vsctl set Interface dpdkvhostuserclient0 > > options:vhost-server-path=/tmp/dpdkvhostuserclient0 > > options:dq-z

[ovs-dev] [PATCH v10] netdev-dpdk: Add support for vHost dequeue zero copy (experimental)

Zero copy is disabled by default. To enable it, set the 'dq-zero-copy' option to 'true' when configuring the Interface: ovs-vsctl set Interface dpdkvhostuserclient0 options:vhost-server-path=/tmp/dpdkvhostuserclient0 options:dq-zero-copy=true When packets from a vHost device with zero copy enable

[ovs-dev] Test

Hi there, This email is to test OVS dev ML. Regards, Nandan Kulkarni ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH v2] ovn-controller: add new external_id 'ovn-cms-options' to Chassis table

Awesome it, this would be very helpful to signal chassis details to the cms in a consistent way. It'd be very helpful if we can get this on 2.9, and although I know it's a feature it's tiny enough and independent enough which may not introduce any regression to OVN. Best, Miguel Ángel On Tue, Ja

Re: [ovs-dev] [PATCH] Show total_ports_on_switch when displaying logical_switch:

On 01/19/2018 11:08 PM, amgin...@gmail.com wrote: From: aginwala e.g. when running ovn-nbctl show ls, it's good to have total ports that are attached to the switch. Signed-off-by: Aliasgar Ginwala --- ovn/utilities/ovn-nbctl.c | 1 + tests/ovn-nbctl.at| 10 ++ 2 files cha

Re: [ovs-dev] [PATCH v4] vswitchd: show DPDK version

> On 01/15/2018 06:21 PM, Matteo Croce wrote: > > Show DPDK version if Open vSwitch is compiled with DPDK support. > > Version can be retrieved with `ovs-switchd --version` or from OVS logs. > > Small change in ovs-ctl to avoid breakage on output change. > > > > Signed-off-by: Matteo Croce > > LG

[ovs-dev] [PATCH v2] ovn-controller: add new external_id 'ovn-cms-options' to Chassis table

This patch makes ovn-controller sets the external_ids key 'ovn-cms-options' to its own Chassis table entry copying its contents from the same external_ids key in the local OpenvSwitch database. The idea behind this patch is to allow setting general options from the CMS Plugin to a particular chass

[ovs-dev] [PATCH] ovn-controller: add new external_id 'ovn-cms-options' to Chassis table

This patch makes ovn-controller sets the external_ids key 'ovn-cms-options' to its own Chassis table entry copying its contents from the same external_ids key in the local OpenvSwitch database. The idea behind this patch is to allow setting general options from the CMS Plugin to a particular chass

[ovs-dev] [PATCH OVS 1/1] tc flower: reorder tunnel encap/decap actions

The tc_flower conversion struct does not consider the order of actions. If an OvS rule matches on a tunnel (decap) and outputs to a new tunnel, the netlink conversion to TC will add the set tunnel key action before the unset, leading to an incorrect TC rule. This patch reorders the netlink generati

Re: [ovs-dev] [PATCH v2] bridge: Fix custom stats' counters leak.

On 01/22/2018 11:55 PM, Ilya Maximets wrote: The caller takes ownership over allocated array of counters. And it must free them. CC: Michal Weglicki Fixes: 971f4b394c6e ("netdev: Custom statistics.") Signed-off-by: Ilya Maximets Acked-by: Mark Michelson --- vswitchd/bridge.c | 1 + 1 f

Re: [ovs-dev] [PATCH v9] netdev-dpdk: Add support for vHost dequeue zero copy (experimental)

On 19.01.2018 20:19, Ciara Loftus wrote: > Zero copy is disabled by default. To enable it, set the 'dq-zero-copy' > option to 'true' when configuring the Interface: > > ovs-vsctl set Interface dpdkvhostuserclient0 > options:vhost-server-path=/tmp/dpdkvhostuserclient0 > options:dq-zero-copy=true >

Re: [ovs-dev] [PATCH v3] netdev-dpdk: fix port addition for ports sharing same PCI id

> -Original Message- > From: Yuanhan Liu [mailto:y...@fridaylinux.org] > Sent: Friday, January 19, 2018 2:48 PM > To: Stokes, Ian > Cc: d...@openvswitch.org; Shahaf Shuler ; Loftus, > Ciara ; Thomas Monjalon ; > Kevin Traynor ; Ilya Maximets > (i.maxim...@samsung.com) ; Olga Shern > > S

[ovs-dev] [PATCH] netdev-dpdk: Refactor custom stats.

This code is overcomplicated and completely unreadable. And a bunch of recently fixed memory leaks confirms that statement. Main concerns that were fixed: * Too big nesting level. * Useless checks like pointer checking after xmalloc. * Misleading comments. * Bad names of the variables. As a bonus

[ovs-dev] Updated Rackspace Users List

style="color:rgb(31,78,121)">Hi,style="color:rgb(31,78,121)">  We have the new updated Rackspace Users lists with emails and complete contact information for your business leads.style="color:rgb(31,78,121)">  We also have other technology users like: AWS, Azure, Heroku, Amazon EC2, Amazon

[ovs-dev] [PATCH] ofproto-dpif-xlate: Fix incorrect handling of return values.

From: Lili Huang The value cookie_offset should be 'size_t' type. Change-Id: Id68b83d26b1235048cbcfd21429ad6915a7a2b36 Signed-off-by: Lili Huang --- ofproto/ofproto-dpif-xlate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ofproto/ofproto-dpif-xlate.c b/ofproto/ofproto-d

Re: [ovs-dev] [dpdk-dev] About : Enable optional dequeue zero copy for vHost User

Hi Which version of dpdk you are using? I have some fixes for dequeue zero copy and now in 18.02-rc1, you can try 18.02-r1. Cheers JJ > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Loftus, Ciara > Sent: Tuesday, January 23, 2018 6:46 PM > To: liyang07 > Cc:

Re: [ovs-dev] mbuf pool sizing

On 01/17/2018 07:48 PM, Venkatesan Pradeep wrote: > Hi, > > Assuming that all ports use the same MTU, in OVS2.8 and earlier, a single > mempool of 256K buffers (MAX_NB_MBUF = 4096 * 64) will be created and shared > by all the ports > > With the OVS2.9 mempool patches, we have port specific all

Re: [ovs-dev] [PATCH v4 1/1] netdev-dpdk: Fix requested MTU size validation.

> -Original Message- > From: Stokes, Ian > Sent: Monday, January 22, 2018 6:27 PM > To: d...@openvswitch.org > Cc: Stokes, Ian ; Kavanagh, Mark B > > Subject: [PATCH v4 1/1] netdev-dpdk: Fix requested MTU size validation. > Hi all, thanks for the work reviewing this, I've applied it to

Re: [ovs-dev] [PATCH v4] vswitchd: show DPDK version

On 01/15/2018 06:21 PM, Matteo Croce wrote: > Show DPDK version if Open vSwitch is compiled with DPDK support. > Version can be retrieved with `ovs-switchd --version` or from OVS logs. > Small change in ovs-ctl to avoid breakage on output change. > > Signed-off-by: Matteo Croce LGTM Acked-by: K

Re: [ovs-dev] About : Enable optional dequeue zero copy for vHost User

Hi, For the meantime this feature is proposed as ‘experimental’ for OVS DPDK. Unless you are transmitting to a NIC, you don’t need to set the n_txq_desc. My testing has been only with a DPDK driver in the guest. Have you tried that option? Thanks, Ciara From: liyang07 [mailto:liyan...@corp.nete

Re: [ovs-dev] [PATCH v9] netdev-dpdk: Add support for vHost dequeue zero copy (experimental)

> -Original Message- > From: Loftus, Ciara > Sent: Friday, January 19, 2018 5:19 PM > To: d...@openvswitch.org > Cc: Loftus, Ciara ; Stokes, Ian > ; jan.scheur...@ericsson.com; ktray...@redhat.com; > i.maxim...@samsung.com > Subject: [PATCH v9] netdev-dpdk: Add support for vHost dequeue zer

[ovs-dev] OVS+DPDK: deadlock and race condtion, which leads OVS deadlock or crash

Hi Yuanha and all, Thanks for review. I change the title and let more people involved. The issues can be reproduced easily with OVS. The steps are below: 1) virsh start vm 2) ovs-vsctl add port 3) delete the port via ovs-vsctl del-port. 4) shutdown VM via vrish destroy. I run a script to repeat

Re: [ovs-dev] [PATCH v5 0/5] OVS-DPDK flow offload with rte_flow

> Hi, > Just added then Napatech NIC supported to the list. > Thanks Finn. I'll be reviewing this series today. Thanks Ian > Finn > > --- > diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst > index 40f9d9649..442848870 100644 > --- a/Documentation/howto/dpdk.rst > +++ b/

Re: [ovs-dev] [PATCH v5 0/5] OVS-DPDK flow offload with rte_flow

Hi, Just added then Napatech NIC supported to the list. Finn --- diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst index 40f9d9649..442848870 100644 --- a/Documentation/howto/dpdk.rst +++ b/Documentation/howto/dpdk.rst @@ -727,3 +727,20 @@ devices to bridge ``br0``. Once co

Re: [ovs-dev] [PATCH V3 0/6] Enable OVS on Linux 4.14 kernel

Hi, Greg. I haven't looked at these in detail, but it doesn't look like NEWS or the FAQ supported kernel list was updated. Would you mind adding those and rebasing against the current master? If you can do that, I'll take a closer look and get them merged into master and branch-2.9. Thanks,